Re: [Computer-go] GCP passing on the staff ...

[Petri Pitkanen]

Just purely curiosity: How strong is Leela now? googling up gives that it
is better than best humasn already? Is that true?

Petri



ma 28. tammik. 2019 klo 23.31 "Ingo Althöfer" (3-hirn-ver...@gmx.de)
kirjoitti:

> Hello,
>
> a central quote from the Leela Github blog at
> https://github.com/gcp/leela-zero/issues/2157
>
> Gian-Carlo Pascutto wrote:
> >> So, practically, I'll keep the current 256x40 running as
> >> is, which probably has a (few?) month(s) to go with a last
> >> learning rate drop or playout increase, at least, but for
> >> the next leap ahead someone else (person or team) will have
> >> to step up and do the necessary work:
>
> So, we are standing at a fork.
> How will the Leela Zero project proceed?
> Who is willing to take central positions in that process?
>
> Many thanks to Gian-Carlo for putting so much energy into
> the project! And many thanks to his wife and family for
> accepting his dedication to computer go and computer chess!
> It has helped our scene so much.
>
> Ingo.
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] New paper by DeepMind

[Petri Pitkanen]

while working at Nokia we revieved what innovations were worth patenting
and how to deal with those we did not see important enough. Sometime we
paid a reseacher from acemia to write a paper and submit for some
conference. There were other methods. But filing just for prior art is way
too expensive.


Petri

ma 10. jouluk. 2018 klo 12.31 Erik van der Werf (erikvanderw...@gmail.com)
kirjoitti:

> Publishing a paper or making your work open source is fine for defensive
> purposes. You just have to make sure you can prove the date. Filing a
> patent application when you have no hope of getting it granted is silly
> because there are cheaper (and IMO nicer) alternatives. Perhaps forcing
> yourself to go through the patent application process helps to increase
> confidence that you have freedom to operate (or find out that you don't),
> but other than that, unless you (or anyone else) could expect to get the
> patent granted it is a waste of time.
>
> On Sun, Dec 9, 2018 at 8:27 PM uurtamo  wrote:
>
>> So published prior art isn't a defense? It's pretty widely publicized
>> what they did and how.
>>
>> The problem I have with most tech patents is when they're overly broad.
>>
>> s.
>>
>> On Sun, Dec 9, 2018, 9:11 AM David Doshay via Computer-go <
>> computer-go@computer-go.org wrote:
>>
>>> Another very important aspect of this discussion is that the US patent
>>> office changed to a ‘first to file’ method of prioritizing patent rights.
>>> This encouraged several patent trolls to try to undercut the true
>>> inventors. So, it is now more important to file for defensive purposes just
>>> to assure that deep pockets like Alpha do not have to pay royalties to
>>> others for their own inventions.
>>>
>>> Many years ago when I worked at NASA we were researching doing a patent
>>> filing for an image processing technique so that we could release it for
>>> public domain use. We found that someone successfully got a patent for
>>> using a bitmap to represent a black-and-white image! It may indeed have
>>> been possible and successful to argue in court that this is obvious to
>>> anyone in the industry and thus should not be granted a patent, but it
>>> would be costly and a bother to have to do so. Likewise for a deep pocket
>>> like Alpha who would be an obvious target for patent trolling if they did
>>> not get this technique labeled as public knowledge quickly enough.
>>>
>>> Cheers,
>>> David
>>>
>>> On Dec 9, 2018, at 8:30 AM, Jim O'Flaherty 
>>> wrote:
>>>
>>> Tysvm for your excellent explanation.
>>>
>>> And now you can see why I mentioned Google's being a member of OIN as a
>>> critical distinction. It strongly increases the weight of 2. And implicitly
>>> reduces the motivation for 1.
>>>
>>>
>>> On Sat, Dec 8, 2018, 8:51 PM 甲斐徳本 >>
 Those are the points not well understood commonly.

 A patent application does two things.  1. Apply for an eventual
 granting of the patent, 2. Makes what's described in it a public knowledge
 as of the date of the filing.
 Patent may be functionally meaningless.  There may be no one to sue.
 And these are huge issues for the point No.1.  However, a strategic patent
 applicants file patent applications for the point No.2 to deny any
 possibility of somebody else obtaining a patent.  (A public knowledge
 cannot be patented.)

 Many companies are trying to figure out how to patent DCNN based AI,
 and Google may be saying "Nope, as long as it is like the DeepMind method,
 you can't patent it."   Google is likely NOT saying "We are hoping to
 obtain the patent, and intend to enforce it."

 Despite many differences in patent law from a country to another, two
 basic purposes of patent are universal: 1. To protect the inventor, and 2.
 To promote the use of inventions by making the details a public knowledge.




 On Sat, Dec 8, 2018 at 12:47 AM uurtamo  wrote:

> What I'm saying is that the patent is functionally meaningless. Who is
> there to sue?
>
> Moreover, there is no enforceable patent on the broad class of
> algorithms that could reproduce these results. No?
>
> s.
>
> On Fri, Dec 7, 2018, 4:16 AM Jim O'Flaherty <
> jim.oflaherty...@gmail.com wrote:
>
>> Tysvm for the clarification, Tokumoto.
>>
>> On Thu, Dec 6, 2018, 8:02 PM 甲斐徳本 >
>>> What's insane about it?
>>> To me, what Jim O'Flaherty stated is common sense in the field of
>>> patents, and any patent attorney would attest to that.  If I may add, 
>>> Jim's
>>> last sentence should read "Google's patent application" instead of
>>> "Google's patent".  The difference is huge, and this may be in the 
>>> heart of
>>> the issue, which is not well understood by the general public.
>>>
>>> In other words, thousands of patent applications are filed in the
>>> world without any hope of the patent eventually being granted, to 

Re: [Computer-go] 9x9 is last frontier?

[Petri Pitkanen]

elo-range in 9x9 smaller than 19x19. One just cannot be hugelyl better than
the other is such limitted game

2018-02-23 21:15 GMT+02:00 Hiroshi Yamashita :

> Hi,
>
> Top 19x19 program reaches 4200 BayesElo on CGOS. But 3100 in 9x9.
> Maybe it is because people don't have much interest in 9x9.
> But it seems value network does not work well in 9x9.
> Weights_33_400 is maybe made by selfplay network. But it is 2946 in 9x9.
> Weights_31_3200 is 4069 in 19x19 though.
>
> In year 2012, Zen played 6 games against 3 Japanese Pros, and lost by 0-6.
> And it seems Zen's 9x9 strength does not change big even now.
> http://computer-go.org/pipermail/computer-go/2012-November/005556.html
>
> I feel there is still enough chance that human can beat best program in
> 9x9.
>
> Thanks,
> Hiroshi Yamashita
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Project Leela Zero

[Petri Pitkanen]

Seems suprisingly strong. Given that no super vcluster availab,´le for
trainning. Have at least on accoutn rated would be nice since in unrated
games people experiment  quite a lot at cost of playing well.

2017-12-29 22:02 GMT+02:00 Brian Sheppard via Computer-go <
computer-go@computer-go.org>:

> Seems like extraordinarily fast progress. Great to hear that.
>
> -Original Message-
> From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf
> Of "Ingo Althöfer"
> Sent: Friday, December 29, 2017 12:30 PM
> To: computer-go@computer-go.org
> Subject: [Computer-go] Project Leela Zero
>
> Hello in the round,
>
> I am not sure how narrowly people from the list are following the progress
> of Gian Carlo Pascutto's project Zero Leela. Therefore, here are some
> impressions.
>
> The project site is:
> http://zero.sjeng.org/
>
> Shortly before Christmas some guys in the German Go mailing list claimed
> that LeelaZero had not yet reached a 25-kyu rank. To get an own impression
> I (with an inactive rating of 18-kyu) went on KGS and played a free game
> against LeelaZSlow. This version takes exactly 28 seconds per move, even in
> trivial situations. Long paragraph, short outcome: I lost clearly. You can
> download the sgf from here:
> http://files.gokgs.com/games/2017/12/21/GoIngo-LeelaZSlow.sgf
>
> In the meantime the KGS versions of Leela have made considerable progress.
> For instance, yesterday and today two 1-dans and a 3-dan were beaten in
> single games.
> However, Leela also has "strange" weaknesses. The most serious one
> concerns hopeless ladders. The only way out for Leela seems to be to play
> early tengen-like moves (as possible ladder breakers).
> At least three versions of LeelaZero are active:
> LeelaZFast, LeelaZSlow, and LeelZeroT.
>
> As soon as a new "best" LeelaZero version has emerged in selfplay runs (of
> length 400 games) it substitutes the previous version for play on KGS.
> Currently this happens 1 or 2 times per day.
>
> Ingo.
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Learning related stuff

[Petri Pitkanen]

>But again: For instance, when a eight year old child starts
>to play violin, is it helpful or not when it had played
>say a trumpet before?

It would be and this is well known in practice. Logic around the music is
the same so hw would learn faster. In the very long run there might be no
wanted effects. i.e. hard to learn away from something too similar. But in
case of trumper and violin no. But lets say 10 years of training violin
played like bluegrass player plays and then switchin to classical. That
would be hard. due required unlearning for which humans do no really have
mechanism for. New skill needs to be learned better thatn the old skill or
time needs to erase the untrained old skill. While the DCNN can learn and
unlearn quite easily

2017-11-22 0:48 GMT+02:00 Álvaro Begué :

> The term you are looking for is "transfer learning": https://en.
> wikipedia.org/wiki/Transfer_learning
>
>
> On Tue, Nov 21, 2017 at 5:27 PM, "Ingo Althöfer" <3-hirn-ver...@gmx.de>
> wrote:
>
>> Hi Erik,
>>
>> > No need for AlphaGo hardware to find out; any
>> > toy problem will suffice to explore different
>> > initialization schemes...
>>
>> I know that.
>>
>> My intention with the question is a different one:
>> I am thinking how humans are learning. Is it beneficial
>> to have learnt related - but different - stuff before?
>> The answer will depend on the case, of course.
>>
>> And in my role as a voyeur, I want to understand if having
>> learnt a Go variant X before turning my interest to a
>> "slightly" different Go variant Y. Do, I want to combine
>> the subject with some entertaining learning process.
>> (For instance, looking at the AlphaGo Zero games from the
>> 72 h experiment in steps of 2 hours was not only insightful
>> but also entertaining.)
>>
>>
>> > you typically want to start with small weights so
>> > that the initial mapping is relatively smooth.
>>
>> But again: For instance, when a eight year old child starts
>> to play violin, is it helpful or not when it had played
>> say a trumpet before?
>>
>> My understanding is that the AlphaGo hardware is standing
>> somewhere in London, idle and waitung for new action...
>>
>> Ingo.
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] what is reachable with normal HW

[Petri Pitkanen]

So If I load latest leela into a laptop (being about KGS 4k) I would expect
to demolished even on 9 stone handicap. Nice

Petri

2017-11-15 13:55 GMT+02:00 Darren Cook :

> > Zero was reportedly very strong with 4 TPU. If we say 1 TPU = 1 GTX 1080
> > Ti...
>
> 4 TPU is 180 TFLOPS, or 45 TFLOPS each [1]
>
> GTX 1080Ti is 11.3 TFLOPs [2], or 9 TFLOPS for the normal 1080.
>
> So 4 TPUs are more like 15-20 times faster than a high-end gaming notebook.
>
> (I'm being pedantic; I expect your main point still stands even if it is
> 20x. And if not, the AlphaZero results were at 5s/move - people wanting
> a world-class game could give it 30s or even 60s/move.)
>
> Darren
>
>
> [1]: https://en.wikipedia.org/wiki/Tensor_processing_unit
> [2]:
> https://www.anandtech.com/show/11180/the-nvidia-geforce-gtx-1080-ti-review
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] what is reachable with normal HW

[Petri Pitkanen]

I think the intereseting question left now is: How strong GO-program one
can have in normal Laptop? TPU and GPU are fine for showing what can be
done but as practical tool for a go player the bot  has to run something
people can afford. And can buy from shop? From KGS 100 list I can spot 8d
bots but I do not know how big HW they are using.

Could todays laptop with best possible SW beat best humans?

Petri
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

and we can allways come up with bizarre situation like casualties insidet
the vehicle vs casualties to persoons outside the vehicle. I am pretty sure
this will a long discussion with huge research gaps on ethics  as well as
in engineering

2017-10-31 7:00 GMT+02:00 Robert Jasiek :

> On 30.10.2017 19:22, Pierce T. Wetter III wrote:
>
>> this car and this child
>>
>
> In Germany, an ethics commission has written ethical guidelines for
> self-driving cars with also the rule to always prefer avoiding casualties
> of human beings.
>
>
> --
> robert jasiek
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

intuition is handy word for truly automated information processing i.e
subconscious.   And everything that train conscious decission making trains
also the subconscious/intuiton. Intuiton nothing mythical just automation
achieved via training

2017-10-29 5:08 GMT+02:00 Thomas Rohde :

> On 2017-10-28 at 16:36, Robert Jasiek  wrote:
>
> > IMO, intuition does not exist; it is nothing but an excuse for not
> understanding subconscious or currently unobservable thinking yet. Can we
> speak of human subconscious thinking, please?
>
> Uhm, I always thought the short word for “subconscious thinking” was
> “intuition” ;-)
>
> Reminds me of “A Table is a Table” (orig. “Ein Tisch ist ein Tisch”), a
> short story by Swiss writer Peter Bichsel
>
> —> https://vimeo.com/11331609 (ten minutes video, English version)
> —> https://vimeo.com/8749843 (German version)
>
> “What's in a name? that which we call a rose
> By any other word would smell as sweet”
> — Shakespeare
>
>
> Greetings, Tom
>
> --
> Thomas Rohde
> Wiesenkamp 12, 29646 Bispingen, GERMANY
> --
> t...@bonobo.com
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

Exactly verbalized rules lose to pure analysis power. Though much chess
intuiton is coded into  evaluation function. Buiding analysis trees to
alfa-beta pruning BUT in quite differently human woudl do it, just basic
idea/ideas are there.

Human intuition is trained with endless repetition. Like IM Jeremy Silman
who went through about hundred games a night while teenager (quite a feat
on actual board) to 'train' his pattern matcher.

I do doubt if anyone coudl codifly that information in fully transferrable
way at all. In teacher-pupil interaction somehow. But as an book, noway.
Hard to say what chess IM is go terms but whole chess Grand master to
Master ranks are within 300 elopoints-. And in upper echelons one Dan rank
is about 250-300 elopoints so IM woudl strongish 6dan perhaps , not quite
7dan.  So 4dan is way better than what I can drema of but still is chess
ranks that woudl be a like Elo 2000 a good player but no way near a master.
So I woudl say that the old way, how ever tedious and non-analytical is
still required to reach the top of game.

But then again teaching method to quickly reach a reasonable strength is
certainly needed. Mayre robert has it, do not know as have not tried

2017-10-28 1:39 GMT+03:00 uurtamo . :

> By way of comparison.
>
> It would be ludicrous to ask a world champion chess player to explain
> their strategy in a "programmable" way. it would certainly result in a
> player much worse than the best computer player, if it were to be coded up,
> even if you spent 40 years decoding intuition, etc, and got it exactly
> correct.
>
> Why do I say this? Because the best human player will lose > 90% of the
> time against the best computer player. And they understand their own
> intuition fairly well.
>
> Do we want to sit down and analyze the best human player's intuition?
> Perhaps. But certainly not to improve the best computer player. It can
> already crush all humans at pretty much every strength.
>
> s.
>
>
> On Fri, Oct 27, 2017 at 10:37 AM, Robert Jasiek  wrote:
>
>> On 27.10.2017 13:58, Petri Pitkanen wrote:
>>
>>> doubt that your theory is any better than some competing ones.
>>>
>>
>> For some specialised topics, it is evident that my theory is better or
>> belongs to the few applicable theories (often by other amateur-player
>> researchers) worth considering.
>>
>> For a broad sense of "covering every aspect of go theory", I ask: what
>> competing theories? E.g., take verbal theory teaching by professional
>> players and they say, e.g., "Follow the natural flow of the game". I have
>> heard this for decades but still do not have the slightest idea what it
>> might mean. It assumes meaning only if I replace it by my theory. Or they
>> say: "Respect the beauty of shapes!" I have no idea what this means.
>>
>> A few particular professional players have reasonable theories on
>> specific topics and resembling methodical approach occurring in my theories.
>>
>> So what competing theories do you mean?
>>
>> The heritage of professional shape examples? If you want to call that
>> theory.
>>
>> As I do know people who are stronger than you and are using different
>>> framework.
>>>
>>
>> Yes, but where do they describe it? Almost all professional players I
>> have asked to explain their decision-making have said that they could not
>> because it would be intuition. A framework that is NOT theory.
>>
>>
>> --
>> robert jasiek
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

You playing strength is anecdotal evidence. And quite often going through
just systematic way your thinking is more valuable than the actual end
product. As it programs you subconscious decision making. You said that it
is not part of your decision making but that is unlikely to be true. People
do not know when subconscious decision are made as the upper layer
rationalizes the decisions afterwards.
https://www.relationshipscoach.co.uk/blog/research-shows-our-subconscious-mind-makes-our-decisions-for-us/

and that is not bad. Your huge effort to become strong player did program
you intuitive decision making to such degree that it is worth listening.

I still would doubt that your theory is any better than some competing
ones. As I do know people who are stronger than you and are using different
framework. Similarity is the directed and intentional search of truth.
Process is probably way more important the result. Obviousl I canno tprove
my point as my evidence is anecdotal

PP

2017-10-26 17:54 GMT+03:00 Robert Jasiek :

> On 26.10.2017 08:52, Petri Pitkanen wrote:
>
>> Unfortunately there is no proof that you principles work better than those
>> form eighties.
>>
>
> No computer-go proof.
>
> There is evidence in the form of my playing strength: with the principles
> "from the eighties", I got to circa 1 kyu. L+D reading practice etc. made
> me 3 dan. Afterwards, almost the only thing that made me stronger to 5 dan
> and then further improved my understanding was the invention of my own
> principles.
>
> My principles etc. also work for (an unknown fraction of) readers of my
> books and for a high percentage of my pupils but I cannot compare what the
> effect on them would have been if instead they would only have learnt the
> principles "from the eighties". I do, however, know that my principles
> provide me with very much more efficient means of teaching contents
> compared to using the principles "from the eighties".
>
> The principles "from the eighties" and my principles can be compared with
> each other. IMO, such a comparison is shocking: the principles "from the
> eighties" are very much weaker on average and altogether convey very much
> less contents.
>
> Nor there is any agreement that your pronciples form any
>> improvement over the old ones.
>>
>
> Only time constraints prevent me from doing an extensive comparison and so
> better support formation of an agreement.
>
> What is missing that I doubt that you can verbalise your go understanding
>> to degree that by applying those principles  I could become substantially
>> better player.
>>
>
> Different players are different. So different that some players claim to
> only learn from examples. Therefore, I cannot know whether you are a player
> who could learn well from principles etc.
>
> - My reading skills would not get any better
>>
>
> Do you say so after having learnt and invested effort in applying the
> contents of Tactical Reading?
>
> Regardless of the possible impact of that book, a great part of reading
> skill must be obtained by reading practice in games and problem solving. If
> your reading is much weaker than your knowledge of go theory, then it may
> be the case that almost only reading practise (plus possibly reading theory
> about improving one's reading practice) can significantly improve your
> strength at the moment.
>
> - your principles are more complex than you understand.
>>
>
> I do not think so:)
>
> Much of you know is
>> automated to degree that it is subconsciousness information.
>>
>
> From ca. 10 kyu to now, especially from 3 dan to now, I have reduced the
> impact of my subconscious thinking on my go decision-making and replaced it
> by knowledge, reading and positional judgement based on knowledge and
> reading. The still remaining subconscious thinking is small. Most of my
> remaining mistakes are related to psychology or subconscious thinking, when
> necessary because of explicit knowledge gaps or thinking time constraints.
>
> Transferring that information if hard.
>>
>
> Transferring it from principles etc. to code - yes.
>
> If you can build Go bot about  KGS 3/4dan strength
>>
>
> Using my approach, I expect several manyears, which I do not have for that
> purpose.
>
>
> --
> robert jasiek
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

Unfortunately there is no proof that you principles work better than those
form eighties. Nor there is any agreement that your pronciples form any
improvement over the old ones. Yes you are a  far better player than me and
shows that you are
- way better at reading
- have hugely better go understanding, principles if you like

What is missing that I doubt that you can verbalise your go understanding
to degree that by applying those principles  I could become substantially
better player. again bulleting
- My reading skills would not get any better hence making much of value any
learning moot. Obviously issue on me not on your principles
- your principles are more complex than you understand. Much of you know is
automated to degree that it is subconsciousness information. Transferring
that information if hard. Usually done by re-playing master games looking
at problems i.e. training the darn neural net in the head

If you can build Go bot about  KGS 3/4dan strength I am more than willing
to admit you are right and would even consider buying your  books.

Petri

2017-10-26 6:21 GMT+03:00 Robert Jasiek :

> On 25.10.2017 18:17, Xavier Combelle wrote:
>
>> exact go theory is full of hole.
>>
>
> WRT describing the whole game, yes, this is the current state. Solving go
> in a mathematical sense is a project for centuries.
>
> Actually, to my knowledge human can't apply only the exact go theory and
>> play a decent game.
>>
>
> Only for certain positions of a) late endgame, b) semeais, c) ko.
>
> If human can't do that, how it will teach a computer to do it magically ?
>>
>
> IIRC, Martin Müller implemented CGT endgames a la Mathematical Go Endgames.
>
> The reason why (b) had became unpopular is because there is no go theory
>> precise enough to implement it as an algorithm
>>
>
> There is quite some theory of the 95% principle kind which might be
> implemented as approximation. E.g. "Usually, defend your weak important
> group." can be approximated by approximating "group", "important" (its loss
> is too large in a quick positional judgement), "weak" (can be killed in two
> successive moves), "defend" (after the move, cannot be killed in two
> successive moves), "usually" (always, unless there are several such groups
> and some must be chosen, say, randomly; the approximation being that the
> alternative strategy of large scale exchange is discarded).
>
> Besides, one must prioritise principles to solve conflicting principles by
> a higher order principle.
>
> IMO, such an expert system combined with tree reading and maybe MCTS to
> emulate reading used when a principle depends on reading can, with an
> effort of a few manyears of implementation, already achieve amateur mid
> dan. Not high dan yet because high dans can choose advanced strategies,
> such as global exchange, and there are no good enough principles for that
> yet, which would also consider necessary side conditions related to
> influence, aji etc. I need to work out such principles during the following
> years. Currently, the state is that weaker principles have identified the
> major topics (influence, aji etc.) to be considered in fights but they must
> be refined to create 95%+ principles.
>
> ***
>
> In the 80s and 90s, expert systems failed to do better than ca. 5 kyu
> because principles were only marginally better than 50%. Today, (my)
> average principles discard the weaker, 50% principles and are ca. 75%.
> Tomorrow, the 75% principles can be discarded for an average of 95%
> principles. Expert systems get their chance again! Their major disadvantage
> remains: great manpower is required for implementation. The advantage is
> semantical understanding.
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

If the AG got better by playing against itself rather than training on
previous good players then I do not thing training data is that important.
Perhaps it is but google has shown that actually u dont need it. Just loads
of processing will do the trick.



2017-10-23 15:05 GMT+03:00 Jim O'Flaherty :

> Couldn't they be useful as part of a set of training data for newly
> trained engines and networks?
>
> On Oct 23, 2017 2:34 AM, "Petri Pitkanen" 
> wrote:
>
>> They are free to use in any attribution. Game score is a reflection of
>> historical fact and hence not copyrightable. Dunno what use them are to
>> anyone though.
>>
>> Petri
>>
>> 2017-10-23 2:29 GMT+03:00 Lucas Baker :
>>
>>> Hi Robert,
>>>
>>> The AlphaGo Zero games are free to use with proper attribution, so
>>> please use them as you like for commentaries as long as you credit DeepMind.
>>>
>>> Best,
>>> Lucas Baker
>>>
>>> On Sun, Oct 22, 2017 at 3:59 PM Robert Jasiek  wrote:
>>>
>>>> AlphaGo Zero games are available as zipped SGF from Deepmind at
>>>> http://www.alphago-games.com/ For earlier AlphaGo games, I have seen
>>>> statements from Deepmind encouraging free use (presuming stating origin,
>>>> of course) so that the games may be commented etc. I cannot find a
>>>> similar statement from Deepmind for the published AlphaGo Zero games.
>>>> Are they for free use or copyrighted? I hope the former so everybody
>>>> including Deepmind can see more commentaries.
>>>>
>>>> --
>>>> robert jasiek
>>>> ___
>>>> Computer-go mailing list
>>>> Computer-go@computer-go.org
>>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>>>
>>> ___
>>> Computer-go mailing list
>>> Computer-go@computer-go.org
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>>
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

[Petri Pitkanen]

They are free to use in any attribution. Game score is a reflection of
historical fact and hence not copyrightable. Dunno what use them are to
anyone though.

Petri

2017-10-23 2:29 GMT+03:00 Lucas Baker :

> Hi Robert,
>
> The AlphaGo Zero games are free to use with proper attribution, so please
> use them as you like for commentaries as long as you credit DeepMind.
>
> Best,
> Lucas Baker
>
> On Sun, Oct 22, 2017 at 3:59 PM Robert Jasiek  wrote:
>
>> AlphaGo Zero games are available as zipped SGF from Deepmind at
>> http://www.alphago-games.com/ For earlier AlphaGo games, I have seen
>> statements from Deepmind encouraging free use (presuming stating origin,
>> of course) so that the games may be commented etc. I cannot find a
>> similar statement from Deepmind for the published AlphaGo Zero games.
>> Are they for free use or copyrighted? I hope the former so everybody
>> including Deepmind can see more commentaries.
>>
>> --
>> robert jasiek
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo Zero

[Petri Pitkanen]

1) There is no such thing and I do doubt if it ever will exist. Even humans
fail elaborate why they know certain things
2) If we are talking about new one. Very few people seen it playing so I
guess we lack the data. For the old we know it made errors, dunno if
analysis points why. Neural nets tend to be black boxes
3) Would it be a bad thing? All thing considered, not just human point of
view

2017-10-20 7:06 GMT+03:00 Robert Jasiek :

> So there is a superstrong neural net.
>
> 1) Where is the semantic translation of the neural net to human theory
> knowledge?
>
> 2) Where is the analysis of the neural net's errors in decision-making?
>
> 3) Where is the world-wide discussion preventing a combination of AI and
> (nano-)robots, which self-replicate or permanently ensure energy access,
> from causing extinction of mankind?
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] agz -- meditations

[Petri Pitkanen]

Cost reduction in IC has reached or is reaching its limits. Intels 5n techk
is not really a 5n and 5n is not really reachable. Not at least without
some seriously new physics and even then there will be hard limits like
quantum un--certainty. This particular chip may get cheaper if it is ever
done in amounts but it is not guaranteed to get lot cheapaer

2017-10-20 6:24 GMT+03:00 Robert Jasiek :

> On 19.10.2017 20:13, Richard Lorentz wrote:
>
>> Silver said "algorithms matter much more than ... computing".
>> Hassabis estimated they used US$25 million of hardware.
>>
>
> Today, it seems 4 TPU cost US$25 million. In 5 or 10 years, every computer
> might have its 4-TPU-chip costing $250, if not $25. At least, I hope.
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo and Perfect Play

[Petri Pitkanen]

Has to be truly far. Even in chess best estimates are that current
computers are still few hundred ELO points away from perfect. In chess on
can make estimates based what draw rates current best  ones would get
against perfect play. Loads of guess work but still reasonable. In go
difference must be higher

2017-08-17 8:24 GMT+03:00 Xavier Combelle :

> According to what happen in chess and according to the tee size of go game
> I would say that astronomically far from perfect play is an astronomical
> understatement.
>
> Le 17 août 2017 07:17, "Cai Gengyang"  a écrit :
>
> Does anyone here know how far AlphaGo is away from perfect play ?
> Estimations ?
>
> GengYang
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Auto Go game recorder

[Petri Pitkanen]

never heard of one for GO. High School kids in Finland made one for chess.
And to get proper picture camera had to located avbovr the board.I suspect
it has to same way in go. So would require some kind on phone stand

Here is start of such project:
https://gogamerecorder.wordpress.com/

SO I guess you nee wait few years

2016-11-25 2:16 GMT+02:00 Hideki Kato :

> Hello everybody,
>
> Chizu Kobayashi 6p is seeking automatic Go game recorders.  Does
> anyone know about that?  An application for mobilephones is the best
> but any system is appriciated.
>
> Best,
> Hideki
> --
> Hideki Kato 
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Interesting talk on The Role of Computers in professional Chess

[Petri Pitkanen]

I am pretty sure new ideas in Josekis will be researched same way. Perhaps
in connection to adjacent corner configurations etc. Full openings in Go do
not exist in that sense they exist in chess.

Petru

2016-09-28 16:38 GMT+03:00 Nils :

> Hello everyone,
> longtime lurker here. I was at a conference at the beginning of the
> summer, and heard a very interesting talk:
>
> Modern Chess Preparation – The Role of Computers in professional Chess
> by Gawain Jones, Chess Grandmaster
> http://events.techcast.com/bigtechday9/barcelona-1615/?q=barcelona-1615
>
> The talk is interesting and worth watching (if a little long). He talks
> (among other things) about where and why computers make sense in
> preparing for and analyzing matches, starting around minute 41 (to about
> 55). I wonder if this is similar to how Go engines are used (or will be
> rather soon as the engines improve), or if Go is sufficiently different
> from chess that the use of engines will be different (i.e. less clear
> "opening lines" etc.)
>
> Cheers
> Nils
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Commonsense Go

[Petri Pitkanen]

he is muted for a good reason. And "classical " approach was done for
decades did no lead much to anything. So I would be interested on the paper
ONLY if author has implemented his/her ideas and measured performance.
Otherwise it would be waste of time with at least 95% probability

Petri

2016-08-12 1:22 GMT+03:00 Gonçalo Mendes Ferreira :

> Hello, I'm sharing with you a document that was shared in the GNU Go
> mailing list and I found interesting. Its author is currently muted from
> this list, but I think it is very much worth sharing here instead.
>
> There haven't been many papers on a classical approach to Go in recent
> years (decade?).
>
> Here it is
> http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2818149
>
> The original thread can be found at
> http://lists.gnu.org/archive/html/gnugo-devel/2016-08/msg2.html
>
> Cheers,
> Gonçalo
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Creating the playout NN

[Petri Pitkanen]

Would the expected improvement be reduced training time or improved
accuracy?


2016-06-11 23:06 GMT+03:00 Stefan Kaitschick :

> If I understood it right, the playout NN in AlphaGo was created by using
> the same training set as the one used for the large NN that is used in the
> tree. There would be an alternative though. I don't know if this is the
> best source, but here is one example: https://arxiv.org/pdf/1312.6184.pdf
> The idea is to teach a shallow NN to mimic the outputs of a deeper net.
> For one thing, this seems to give better results than direct training on
> the same set. But also, more importantly, this could be done after the
> large NN has been improved with selfplay.
> And after that, the selfplay could be restarted with the new playout NN.
> So it seems to me, there is real room for improvement here.
>
> Stefan
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Commercial Go software and high-end users

[Petri Pitkanen]

Chess was popular everywhere so the barriers were relatively small. As one
chess writer said it. There are moer chess titles written than all other
hobby titles combined. Dunno who reads all of them.

But I do doubt if strong go programs give too much for analysis. Even if
they are 1p and can show you a better move it is not worth much for a human
when there is no reasoning available how to zoom into that move. Even in
chess no-one really gains form computer analysis. After your own analysis
you can check if you missed an tactic, but as for strategy, dont think so

So pro-level-go-teaching-program would be a another decades long problem to
solve

2016-05-30 23:49 GMT+03:00 Petr Baudis :

>   Hi!
>
>   Couple of ideas.
>
> On Mon, May 30, 2016 at 06:19:39AM +0200, "Ingo Althöfer" wrote:
> > One point is: The absolute strength of the program need not to be
> > better than the strength of the player who uses it for analysis purposes.
> > It is enough that the program is tactically strong.
>
>   But strong Go programs are traditionally strategically strong, but
> tactically *weak*. We still don't have a good publicly available tsumego
> solver.  I think this makes their capabilities a lot less useful for
> game analysis.
>
> > Another point: Once you have a database program with nice functionality,
> > it is only a question of short time until it is supported by playing
> > programs.
>
>   (I think we have pretty good web-based Go database engines now.)
>
> > > On the other hand, commercial engines are probably close to breaking
> the
> > > 1p barrier soon. At which point they'll become analysis tools even for
> > > the higher echelon of players, if initial resistance to "a new thing"
> > > can be overcome.
> >
> > And for that it would be very helpful to have a few popular top players
> > using it.
>
>   So my main hypothesis is that the English-speaking market is very
> small, and the East Asian language barrier(s) prevent a lot of network
> effects to kick in; the Western audience is small and the barrier is
> hard to overcome.  (In the Chess world, there probably was
> English-Russian barrier but the player distribution is still a lot
> more even, imho.)
>
> --
> Petr Baudis
> If you have good ideas, good data and fast computers,
> you can do almost anything. -- Geoffrey Hinton
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Beginner question : how to choose a board representation

[Petri Pitkanen]

There are several open source go programs. I would start by investigating
Fuego and Pachi code

2016-04-10 11:34 GMT+03:00 Gonçalo Mendes Ferreira :

> There isn't a lot of info on this[1], so it will probably be a hard
> journey for a fast representation. But the things a Go board
> representation usually focus on are
>
> 1. simulating play and then undoing (or telling what happens after a
> play: liberties left, stone captures)
> 2. fast pattern hashing
> 3. ascertaining qualities of groups of stones, safety, neighbors, etc
>
> The need for these things makes itself apparent little by little.
>
> Pachi has its state representation commented a lot, maybe even too much:
> https://github.com/pasky/pachi/blob/master/board.h
>
> I think the starting point of any representation is that a single point
> is needed for testing ko. :-)
>
> [1] Some actual examples:
> Emil H.J. Nijhuis's thesis, "Learning Patterns in the Game of Go"
> Martin Müller, "Computer Go" (2002)
> https://www.gnu.org/software/gnugo/gnugo_17.html
> https://www.gnu.org/software/gnugo/gnugo_15.html
>
> Gonçalo
>
>
> On 10/04/2016 09:00, Oliver Lewis wrote:
> > There's a discussion of some of the issues in Petr Baudis' PhD thesis:
> > http://pachi.or.cz/
> >
> >
> >
> > On Sun, Apr 10, 2016 at 9:19 AM, Jean-Francois Romang  >
> > wrote:
> >
> >> Hello to everyone ; I'm a newcomer in this list and computer go
> >> programming. I have a chess programming background, but I want to start
> >> something new. :-)
> >> I'm currently in the early phases of developing GTP compatible go
> engine ;
> >> now it's time for me to choose a board representation : are there some
> >> articles or tips on this ?
> >> Thanks,
> >> Jean-Francois
> >> ___
> >> Computer-go mailing list
> >> Computer-go@computer-go.org
> >> http://computer-go.org/mailman/listinfo/computer-go
> >
> >
> >
> > ___
> > Computer-go mailing list
> > Computer-go@computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> >
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Petri Pitkanen]

Since there are only two possible outcomes it pretty much normal. Actually
binomial which will converge to normal given enough samples

Only thing that cans distort is that consecutive games are not
independent (which
is probably the case but do they have positive or negative correlation?)

2016-03-30 13:06 GMT+03:00 Рождественский Дмитрий :

> I think the error here is that the game outcome is not a normaly
> distributed random value.
>
> Dmitry
>
> 30.03.2016, 12:57, "djhbrown ." :
> > Simon wrote: "I was discussing the results with a colleague outside
> > of the Game AI area the other day when he raised
> > the question (which applies to nearly all sporting events,
> > given the small sample size involved)
> > of statistical significance - suggesting that on another week
> > the result might have been 4-1 to Lee Sedol."
> >
> > call me naive, but perhaps you could ask your colleague to calculate
> > the probability one of side winning 4 games out of 5, and then say
> > whether that is within 2 standard deviations of the norm.
> >
> > his suggestion is complete nonsense, regardless of the small sample
> > size. perhaps you could ask a statistician next time.
> >
> > --
> > patient: "whenever i open my mouth, i get a shooting pain in my foot"
> > doctor: "fire!"
> > http://sites.google.com/site/djhbrown2/home
> > https://www.youtube.com/user/djhbrown
> > ___
> > Computer-go mailing list
> > Computer-go@computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

[Petri Pitkanen]

I would second this. computers in chess do not teach anything. Computer can
show you the great move but cannot explain it.

Probably as hard problem to crack as was making a good computer go

2016-03-14 16:22 GMT+02:00 Robert Jasiek :

> On 14.03.2016 08:59, Jim O'Flaherty wrote:
>
>> an AI player who becomes a better and better teacher.
>>
>
> But you are aware that becoming a stronger AI player does not equal
> becoming a stronger teacher? Teachers also need to (translate to and)
> convey human knowledge and reasoning, and adapt to the specific pupils'
> needs (incl. reasoning, subconscious thinking and psychology) while
> interacting with human language specialised in go language. Solve two dozen
> AI tasks, combine them and then, maybe, you get the equivalent of a
> teacher. [FYI, I have taught 100+ regular single go pupils since 2008, and
> groups of pupils.]
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

[Petri Pitkanen]

For Go there is no way to estimate how much stonger one get. But in chess
it can be estimated (not proven) based on what is evident currently, like
top programs never lose on white even against other top program. There is
no way anyone is going to make chess program that beats current top program
3 times out for.  So for chess we can assume that we so close to point
where program can hold draw against anyone that limit can be estimated

go is in many ways very different thing.  Computer Go is now reached
something that happened in chess either late eighties or late nineties
depending interpretation

petri

2016-03-14 16:11 GMT+02:00 Robert Jasiek :

> On 14.03.2016 09:33, Petri Pitkanen wrote:
>
>> And being 600 elo points above best human you are pretty close  to best
>> possible play.
>>
>
> You do not have any evidence for such a limit.
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

[Petri Pitkanen]

And being 600 elo points above best human you are pretty close  to best
possible play. I think it is alreasy possible in chess to estimate max elo
and they are  pretty close to it. All of them. In chess there is no real
incentive to get better, if draw rate is around 97% what would be the
point? obviously more computing wil produce 100% draw rate and then it is
finished. And they all all good enough to see what you could have done
otherwise in your game

But in GO no such issues exist. Alpha go certainly is nowhere that strong.
It will take some time before any go program is 400 points stronger than
strongest human. And at that point is starts to be strong enough for all
practical purposes.  And resources available for research will decline, if
not earlier. I mean if only meaningful opponent is other program it will
just as interesting as computer chess. No one really follows it exect
programmers. No one has arranged a human match in ten years. Well there
have been some with handicaps, but no big interest there either

2016-03-14 9:59 GMT+02:00 Jim O'Flaherty :

> "Who cares if the best chess program is 400 or 600 points stonger than
> best human. They are strong enough."
>
> This is a very limited view of this domain to think the only intention in
> creating a Go AI is to play against humans and beat them. There is a much
> larger and richer world of values we get to explore, both inside and
> outside of Go, as we continue to progress on this.
>
> I want AI players MUCH stronger than humans are at the current time. And I
> think there are many who would like to see much stronger programs than
> humans for plenty of reasons. One is to see where humans have gotten stuck
> in local optimas playing with each other exclusively. Another is we will
> learn all sorts of things about the limits and biases of human cognition
> from an AI player who becomes a better and better teacher. Another, the
> closer the computer gets to playing "ideal Go", the more some of us will
> enjoy the utter beauty of its producing something human minds could not
> directly perceive much less achieve. I am sure there are others. These were
> the ones that just sprung to mind without much effort.
>
>
>
> On Mon, Mar 14, 2016 at 2:07 AM, Petri Pitkanen <
> petri.t.pitka...@gmail.com> wrote:
>
>> Even though the chess SW analyzes less positions/second than earlier it
>> does not mean it is less dependent of good HW. Complex move selection and
>> smart evaluation do need more CPU as well. There are advances like NULL
>> move pruning that reduce the amount of CPU required but still it is very
>> much HW sport.
>>
>> Though just about nay modern phone/laptop had enough of juice to beat any
>> human, So it is rather boring  anyway. Who cares if the best chess program
>> is 400 or 600 points stonger than best human. They are strong enough.
>>
>> In go getting pro strenght to a mobile phone may take quite a while
>>
>> Petri
>>
>> 2016-03-13 21:55 GMT+02:00 Brian Cloutier :
>>
>>> >  not because of a new better algorithm but because the Deep Blue's
>>> 11.38 GFLOP power is available on desktop from about 2006F
>>>
>>> This isn't true, modern chess engines look at far fewer positions than
>>> Deep Blue did.
>>>
>>> From wikipedia <https://en.wikipedia.org/wiki/Computer_chess>: "Chess
>>> engines continue to improve. In 2009, chess engines running on slower
>>> hardware have reached the grandmaster level. A mobile phone won a category
>>> 6 tournament with a performance rating 2898: chess engine Hiarcs 13 running
>>> inside Pocket Fritz 4 on the mobile phone HTC Touch HD won the Copa
>>> Mercosur tournament in Buenos Aires, Argentina with 9 wins and 1 draw on
>>> August 4–14, 2009.[20] Pocket Fritz 4 searches fewer than 20,000 positions
>>> per second.[21] This is in contrast to supercomputers such as Deep Blue
>>> that searched 200 million positions per second."
>>>
>>> From Quora
>>> <https://www.quora.com/How-does-Deep-Blues-playing-strength-and-algorithms-compare-to-modern-chess-engines-eg-Houdini/answer/Andrew-Ng-4>:
>>> " In such, it could calculate 200 million moves per second. This raw,
>>> brute-force approach made Deep Blue such a challenge to Kasparov. Today,
>>> the strength of engines like Deep Fritz, Houdini, and Rybka is rooted in
>>> the software rather than the dedicated chess hardware. These engines are
>>> far more efficient, using specialized heuristics to evaluate far less moves
>>> than Deep Blue, but to a greater depth of variation. For comparison, a
>>> de

Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

[Petri Pitkanen]

Even though the chess SW analyzes less positions/second than earlier it
does not mean it is less dependent of good HW. Complex move selection and
smart evaluation do need more CPU as well. There are advances like NULL
move pruning that reduce the amount of CPU required but still it is very
much HW sport.

Though just about nay modern phone/laptop had enough of juice to beat any
human, So it is rather boring  anyway. Who cares if the best chess program
is 400 or 600 points stonger than best human. They are strong enough.

In go getting pro strenght to a mobile phone may take quite a while

Petri

2016-03-13 21:55 GMT+02:00 Brian Cloutier :

> >  not because of a new better algorithm but because the Deep Blue's 11.38
> GFLOP power is available on desktop from about 2006F
>
> This isn't true, modern chess engines look at far fewer positions than
> Deep Blue did.
>
> From wikipedia : "Chess
> engines continue to improve. In 2009, chess engines running on slower
> hardware have reached the grandmaster level. A mobile phone won a category
> 6 tournament with a performance rating 2898: chess engine Hiarcs 13 running
> inside Pocket Fritz 4 on the mobile phone HTC Touch HD won the Copa
> Mercosur tournament in Buenos Aires, Argentina with 9 wins and 1 draw on
> August 4–14, 2009.[20] Pocket Fritz 4 searches fewer than 20,000 positions
> per second.[21] This is in contrast to supercomputers such as Deep Blue
> that searched 200 million positions per second."
>
> From Quora
> :
> " In such, it could calculate 200 million moves per second. This raw,
> brute-force approach made Deep Blue such a challenge to Kasparov. Today,
> the strength of engines like Deep Fritz, Houdini, and Rybka is rooted in
> the software rather than the dedicated chess hardware. These engines are
> far more efficient, using specialized heuristics to evaluate far less moves
> than Deep Blue, but to a greater depth of variation. For comparison, a
> decent personal computer running Rybka can evaluate up to 8 million moves
> per second"
>
> I agree that Google is likely to move on but AlphaGo is by no means the
> final word in computer go. I'm excited to see the developments that will be
> required to make a program with the same strength possible on your phone.
>
> On Fri, Mar 11, 2016 at 4:17 AM Рождественский Дмитрий 
> wrote:
>
>> I think that a desktop computer's calculating power appear to develop to
>> a necessary level sooner then the algorithm may be optimized to use the
>> power nowdays available. For example, I belive that chess programs run on a
>> desktop well not because of a new better algotrithm but because the Deep
>> Blue's 11.38 GFLOP power is available on desktop from about 2006, in ten
>> years only. So I think the speculation that Deep Mind will change the
>> objective to a more advanced task is right :)
>>
>> Dmitry
>>
>> 11.03.2016, 14:28, "Darren Cook" :
>> >>>  global, more long-term planning. A rumour so far suggests to have
>> used the
>> >>>  time for more learning, but I'd be surprised if this should have
>> sufficed.
>> >>
>> >>  My personal hypothesis so far is that it might - the REINFORCE might
>> >>  scale amazingly well and just continuous application of it...
>> >
>> > Agreed. What they have built is a training data generator, that can
>> > churn out 9-dan level moves, 24 hours a day. Over the years I've had to
>> > throw away so many promising ideas because they came down to needing a
>> > 9-dan pro to, say, do the tedious job of ranking all legal moves in each
>> > test position.
>> >
>> > What I'm hoping Deep Mind will do next is study how to maintain the same
>> > level but using less hardware, until they can shrink it down to run on,
>> > say, a high-end desktop computer. The knowledge gained obviously has a
>> > clear financial benefit just in running costs, and computer-go is a nice
>> > objective domain to measure progress. (But the cynic in me suspects
>> > they'll just move to the next bright and shiny AI problem.)
>> >
>> > Darren
>> >
>> > ___
>> > Computer-go mailing list
>> > Computer-go@computer-go.org
>> > http://computer-go.org/mailman/listinfo/computer-go
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] AlphaGo won the second game!

[Petri Pitkanen]

This time I think game was tougher. Though too weak to judge. At the end
sacrifice a fistfull stones does puzzle me, but again way too weak to
analyze it.

It seem Lee Sedol is lucky if he wins a game

2016-03-10 12:39 GMT+02:00 Petr Baudis :

> On Wed, Mar 09, 2016 at 09:05:48PM -0800, David Fotland wrote:
> > I predicted Sedol would be shocked.  I'm still routing for Sedol.  From
> Scientific American interview...
> >
> > Schaeffer and Fotland still predict Sedol will win the match. “I think
> the pro will win,” Fotland says, “But I think the pro will be shocked at
> how strong the program is.”
>
> In that case it's time for Lee Sedol to start working hard on turning
> this match around, because AlphaGo won the second game too! :)
>
> Petr Baudis
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

[Petri Pitkanen]

Opent to intepretation if this method is brute force. I think it i. Uses
huge amounts of CPU power to run simulations and evaluate NN's. Even in
chess it was not just about tree search, it needs evaluationfunction ot
make sense of the search

2016-02-24 6:52 GMT+02:00 muupan :

> Congratulations, people at DeepMind! Your paper is very interesting to
> read.
>
> I have a question about the paper. On policy network training it says
>
> > On the first pass through the training pipeline, the baseline was set to
> zero; on the second pass we used the value network vθ(s) as a baseline;
>
> but I cannot find any other description about the "second pass". What is
> it? It uses vθ(s), so at least it is done after training vθ(s). Is it that
> after completing the whole training pipeline depicted in Fig. 1, only the
> RL policy network training part is repeated? Or training vθ(s) is also
> repeated? Is the second pass the last pass, or there are more passes? Sorry
> if I just missed the relevant part of the paper.
>
>
> 2016-02-13 12:21 GMT+09:00 John Tromp :
>
>> On Wed, Jan 27, 2016 at 1:46 PM, Aja Huang  wrote:
>> > We are very excited to announce that our Go program, AlphaGo, has
>> beaten a
>> > professional player for the first time. AlphaGo beat the European
>> champion
>> > Fan Hui by 5 games to 0.
>>
>> It's interesting to go back nearly a decade and read this 2007 article:
>>
>> http://spectrum.ieee.org/computing/software/cracking-go
>>
>> where Feng-Hsiung Hsu, Deep Blue's lead developer, made this prediction:
>>
>> "Nevertheless, I believe that a world-champion-level Go machine can be
>> built within 10 years"
>>
>> Which now appears to be spot on. March 9 cannot come soon enough...
>> The remainder of his prediction rings less true though:
>>
>> ", based on the same method of intensive analysis—brute force,
>> basically—that Deep Blue employed for chess".
>>
>> regards,
>> -John
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Match Date: March 09 - 15

[Petri Pitkanen]

Still no time limits. I would assume that very short time limits help
computer, not very sure though


2016-02-06 14:40 GMT+02:00 "Ingo Althöfer" <3-hirn-ver...@gmx.de>:

> Hello,
>
> on the Alpha-Go website a date for the match between
> Lee Sedol and Alpha-Go is given:
> 5 rounds, to be played in Seoul on
>
> * Wednesday, March 09
> * Thursday, March 10
>
> * Saturday, March 12
> * Sunday, March 13
>
> * Tuesday, March 15
>
> It seems that March 11 and 14 are rest days.
>
> http://deepmind.com/alpha-go.html
>
> Ingo.
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] What hardware to use to train the DNN

[Petri Pitkanen]

Welll, David is making a product. Making a product is 'trooper' solution
unless you are making very specific product to a very narrow target group,
willing to pay thousands for single license

Petri

2016-02-04 23:50 GMT+02:00 uurtamo . :

> David,
>
> You're a trooper for doing this in windows. :)
>
> The OS overhead is generally lighter if you use unix; even the most modern
> windows versions have a few layers of slowdown. Unix (for better or worse)
> will give you closer, easier access to the hardware, and closer, easier
> access to halting your machine if you are deep in the guts. ;)
>
> s.
>
>
> On Tue, Feb 2, 2016 at 10:25 AM, David Fotland 
> wrote:
>
>> Detlef, Hiroshi, Hideki, and others,
>>
>> I have caffelib integrated with Many Faces so I can evaluate a DNN.
>> Thank you very much Detlef for sample code to set up the input layer.
>> Building caffe on windows is painful.  If anyone else is doing it and gets
>> stuck I might be able to help.
>>
>> What hardware are you using to train networks?  I don’t have a
>> cuda-capable GPU yet, so I'm going to buy a new box.  I'd like some
>> advice.  Caffe is not well supported on Windows, so I plan to use a Linux
>> box for training, but continue to use Windows for testing and development.
>> For competitions I could use either windows or linux.
>>
>> Thanks in advance,
>>
>> David
>>
>> > -Original Message-
>> > From: Computer-go [mailto:computer-go-boun...@computer-go.org] On
>> Behalf
>> > Of Hiroshi Yamashita
>> > Sent: Monday, February 01, 2016 11:26 PM
>> > To: computer-go@computer-go.org
>> > Subject: *SPAM* Re: [Computer-go] DCNN can solve semeai?
>> >
>> > Hi Detlef,
>> >
>> > My study heavily depends on your information. Especially Oakfoam code,
>> > lenet.prototxt and generate_sample_data_leveldb.py was helpful. Thanks!
>> >
>> > > Quite interesting that you do not reach the prediction rate 57% from
>> > > the facebook paper by far too! I have the same experience with the
>> >
>> > I'm trying 12 layers 256 filters, but it is around 49.8%.
>> > I think 57% is maybe from KGS games.
>> >
>> > > Did you strip the games before 1800AD, as mentioned in the FB paper? I
>> > > did not do it and was thinking my training is not ok, but as you have
>> > > the same result probably this is the only difference?!
>> >
>> > I also did not use before 1800AD. And don't use hadicap games.
>> > Training positions are 15693570 from 76000 games.
>> > Test positions are   445693 from  2156 games.
>> > All games are shuffled in advance. Each position is randomly rotated.
>> > And memorizing 24000 positions, then shuffle and store to LebelDB.
>> > At first I did not shuffle games. Then accuracy is down each 61000
>> > iteration (one epoch, 256 mini-batch).
>> > http://www.yss-aya.com/20160108.png
>> > It means DCNN understands easily the difference 1800AD games and  2015AD
>> > games. I was surprised DCNN's ability. And maybe 1800AD games  are also
>> > not good for training?
>> >
>> > Regards,
>> > Hiroshi Yamashita
>> >
>> > - Original Message -
>> > From: "Detlef Schmicker" 
>> > To: 
>> > Sent: Tuesday, February 02, 2016 3:15 PM
>> > Subject: Re: [Computer-go] DCNN can solve semeai?
>> >
>> > > Thanks a lot for sharing this.
>> > >
>> > > Quite interesting that you do not reach the prediction rate 57% from
>> > > the facebook paper by far too! I have the same experience with the
>> > > GoGoD database. My numbers are nearly the same as yours 49% :) my net
>> > > is quite simelar, but I use 7,5,5,3,3, with 12 layers in total.
>> > >
>> > > Did you strip the games before 1800AD, as mentioned in the FB paper? I
>> > > did not do it and was thinking my training is not ok, but as you have
>> > > the same result probably this is the only difference?!
>> > >
>> > > Best regards,
>> > >
>> > > Detlef
>> >
>> > ___
>> > Computer-go mailing list
>> > Computer-go@computer-go.org
>> > http://computer-go.org/mailman/listinfo/computer-go
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] *****SPAM***** Re: What hardware to use to train the DNN

[Petri Pitkanen]

At least on digital filter time increases non-linearly - you can think NN
as non-linear FIR. And multilayer structure should make this harder, if you
think of it . So some tricks to speed it up might be necessary. dunno about
NN but on digital filters one trick was to train first part of filter and
only after it has achieved something adapt all weights, may not be
applicable here.

PP

2016-02-02 20:38 GMT+02:00 David Fotland :

> How long does it take to train one of your nets?  Is it safe to assume
> that training time is roughly proportional to the number of neurons in the
> net?
>
> Thanks,
>
> David
>
> > -Original Message-
> > From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf
> > Of Detlef Schmicker
> > Sent: Tuesday, February 02, 2016 10:35 AM
> > To: computer-go@computer-go.org
> > Subject: *SPAM* Re: [Computer-go] What hardware to use to train
> > the DNN
> >
> > -BEGIN PGP SIGNED MESSAGE-
> > Hash: SHA1
> >
> > Hi David,
> >
> > I use Ubuntu 14.04 LTS with a NVIDIA GTX970 Graphic card (and i7-4970k,
> > but this is not important for training I think) and installed CUDNN v4
> > (important, at least a factor 4 in training speed).
> >
> > This Ubuntu version is officially supported by Cuda and I did only have
> > minor problems if an Ubuntu update updated the graphics driver: I had 2
> > times in the last year to reinstall cuda (a little ugly, as the graphic
> > driver did not work after the update and you had to boot into command
> > line mode).
> >
> > Detlef
> >
> > Am 02.02.2016 um 19:25 schrieb David Fotland:
> > > Detlef, Hiroshi, Hideki, and others,
> > >
> > > I have caffelib integrated with Many Faces so I can evaluate a DNN.
> > > Thank you very much Detlef for sample code to set up the input layer.
> > > Building caffe on windows is painful.  If anyone else is doing it and
> > > gets stuck I might be able to help.
> > >
> > > What hardware are you using to train networks?  I don t have a
> > > cuda-capable GPU yet, so I'm going to buy a new box.  I'd like some
> > > advice.  Caffe is not well supported on Windows, so I plan to use a
> > > Linux box for training, but continue to use Windows for testing and
> > > development.  For competitions I could use either windows or linux.
> > >
> > > Thanks in advance,
> > >
> > > David
> > >
> > >> -Original Message- From: Computer-go
> > >> [mailto:computer-go-boun...@computer-go.org] On Behalf Of Hiroshi
> > >> Yamashita Sent: Monday, February 01, 2016 11:26 PM To:
> > >> computer-go@computer-go.org Subject: *SPAM* Re:
> > >> [Computer-go] DCNN can solve semeai?
> > >>
> > >> Hi Detlef,
> > >>
> > >> My study heavily depends on your information. Especially Oakfoam
> > >> code, lenet.prototxt and generate_sample_data_leveldb.py was helpful.
> > >> Thanks!
> > >>
> > >>> Quite interesting that you do not reach the prediction rate 57% from
> > >>> the facebook paper by far too! I have the same experience with the
> > >>
> > >> I'm trying 12 layers 256 filters, but it is around 49.8%. I think 57%
> > >> is maybe from KGS games.
> > >>
> > >>> Did you strip the games before 1800AD, as mentioned in the FB paper?
> > >>> I did not do it and was thinking my training is not ok, but as you
> > >>> have the same result probably this is the only difference?!
> > >>
> > >> I also did not use before 1800AD. And don't use hadicap games.
> > >> Training positions are 15693570 from 76000 games. Test
> > >> positions are   445693 from  2156 games. All games are shuffled
> > >> in advance. Each position is randomly rotated. And memorizing
> > >> 24000 positions, then shuffle and store to LebelDB. At first I did
> > >> not shuffle games. Then accuracy is down each 61000 iteration (one
> > >> epoch, 256 mini-batch). http://www.yss-aya.com/20160108.png
> > >> It means DCNN understands easily the difference 1800AD games and
> > >> 2015AD games. I was surprised DCNN's ability. And maybe 1800AD games
> > >> are also not good for training?
> > >>
> > >> Regards, Hiroshi Yamashita
> > >>
> > >> - Original Message - From: "Detlef Schmicker"
> > >>  To:  Sent: Tuesday,
> > >> February 02, 2016 3:15 PM Subject: Re: [Computer-go] DCNN can solve
> > >> semeai?
> > >>
> > >>> Thanks a lot for sharing this.
> > >>>
> > >>> Quite interesting that you do not reach the prediction rate 57% from
> > >>> the facebook paper by far too! I have the same experience with the
> > >>> GoGoD database. My numbers are nearly the same as yours 49% :) my
> > >>> net is quite simelar, but I use 7,5,5,3,3,
> > >>> with 12 layers in total.
> > >>>
> > >>> Did you strip the games before 1800AD, as mentioned in the FB paper?
> > >>> I did not do it and was thinking my training is not ok, but as you
> > >>> have the same result probably this is the only difference?!
> > >>>
> > >>> Best regards,
> > >>>
> > >>> Detlef
> > >>
> > >> ___ Computer-go mailing
> > >> list Computer-go@compute

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

[Petri Pitkanen]

Explaining why the move is good in human terms is useless goal. Good chess
programs cannot do it nor it is meaningful. As the humans and computers
have vastly different approach to selecting a move then  by the definition
have reasons for moves. As an example your second item 'long-term aji', For
human an important short cut but computer a mere result for seeing far
enough in the future or combining several features of postion into
non-linear/linear computation.

Petri

2016-02-01 2:36 GMT+02:00 Robert Jasiek :

> On 31.01.2016 20:28, Peter Drake wrote:
>
>> pick a new research topic.
>>
>
> - explain by the program to human players why MC / DNN play is good in
> terms of human understanding of the game
> - incorporate the difficult parts, such as long-term aji
> - solve the game: prove the correct score, prove a weak solution, prove a
> strong solution [These mathematics keep us busy for at least 400 years
> unless bot research occurs earlier.]
> - create computers that act as mathematicians incl. creativity, invention
> of propositions and their proving [so that the bot researchers can solve
> the game faster]
> - teach the computer expert knowledge so that a) MC / DNN bots become even
> stronger and b) programs can teach with explanation and reasoning
> understood by human pupils
> - apply computer go research to other fields while ensuring that the
> humans cannot be the victims of bugs and ambiguous responsibilty towards
> law and ethics [medicin or cars: who goes to jail if AI kills people, how
> to prevent AI from ruling the world]
> - Play "Conway / Jasiek": modify the rules, invent new games, apply
> computers.
>
> Enough for research for centuries if not millenia, I'd say.
>
> "Game over / intelligence solved" - never heard greater nonsense before.
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] A proposition to improve neural network based on min max

[Petri Pitkanen]

i think similar approaches have been done. I can recall seeing it. Though
in Backgammon they did train only by endresult and seemed to work fine.
Originally anyway, now the have separate NN-for certain phases of the game

2016-01-30 18:07 GMT+02:00 Xavier Combelle :

> I had got an idea but I don't think I'm strong enough programmer to
> implement it. (In particular I know quite nothing about neural network)
> So I submit it here.
>
> If we have a neural network which is able to evaluate all the positions of
> a board.
> The following might help to improve it.
>
> From a position given:
> check the max value of all the evaluations
> go to the next level in the tree
> check the min value of all the evaluations
> if the min value < max value train the network at the root level to target
> max value for the original position
> else go to next level and continue
>
> The reason why I think it could help is because the evaluation at a deeper
> level
> should be easier and so better than at a less deep level.
>
> Please give all your feedback on this idea (even: it's a stupid idea/you
> should implement it are welcome)
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Neural Nets to compare human playing strength

[Petri Pitkanen]

I do not think such exercise would give any meaningful results.  NN would
not imitate it's 'hero' 1-1 not even close

Funny such discussion keep on going on in Chess and Go, in chess i think
Steiniz would be wiped of board by best players of today, but still he
would be way better as he created much of modern chess anyway. I am pretty
sure such players exists in Go as well

2016-01-30 14:23 GMT+02:00 "Ingo Althöfer" <3-hirn-ver...@gmx.de>:

> Hi,
>
> in a German computer-go subforum we have a discussion which
> involves a comparison of the "absolute" playing strengths of
> current hero Lee Sedol and Shusaku (1829-1862).
> http://senseis.xmp.net/?Shusaku
> It is not possible to let them play a match against each other.
>
> But what about the following: Build two neural nets A and B with the same
> overall structure. Let A be trained with the games of Sedol, and B
> be trained with the games of Shusaku. Then let go bots based on A
> and B play against each other. Would the outcome typically say something
> about the playing strengths of Sedol and Shusaku in comparison?
>
> Ingo.
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

[Petri Pitkanen]

I think such analysis might  not bee too usefull. At least chess players
think it is not very usefull. Usually for learning you need "wake-up" your
brains so computer analysis without reasons probabaly on marginally useful.
But very entertaining

2016-01-28 13:27 GMT+02:00 Michael Markefka :

> I think many amateurs would already benefit from a simple blunder
> check and a short list of viable alternatives and short continuations
> for every move.
>
> If I could leave my PC running over night for a 30s/move analysis at
> 9d level and then walk through my game with that quality of analysis,
> I'd be more than satisfied.
>
>
> On Thu, Jan 28, 2016 at 7:42 AM, Robert Jasiek  wrote:
> > Congratulations to the researchers!
> >
> > On 27.01.2016 21:10, Michael Markefka wrote:
> >>
> >> I really do hope that this also turns into a good analysis and
> >> teaching tool for human player. That would be a fantastic benefit from
> >> this advancement in computer Go.
> >
> >
> > The programs successful as computer players mostly rely on computation
> power
> > for learning and decision-making. This can be used for teaching tools
> that
> > do not need to provide text explanations and other reasoning to the human
> > pupils: computer game opponent, life and death playing opponent,
> empirical
> > winning percentages of patterns etc.
> >
> > Currently such programs do not provide sophisticated explanations and
> > reasoning about tactical decision-making, strategy and positional
> judgement
> > fitting human players' / pupils' conceptual thinking.
> >
> > If always correct teaching is not the aim (but if a computer teacher may
> err
> > as much as a human teacher errs), in principle it should be possible to
> > combine the successful means of using computation power with the
> reasonably
> > accurate human descriptions of sophisticated explanations and reasoning.
> > This requires implementation of expert system knowledge adapted from the
> > best (the least ambiguous, the most often correct / applicable)
> descriptions
> > of human-understandable go theory and further research in the latter.
> >
> > --
> > robert jasiek
> >
> > ___
> > Computer-go mailing list
> > Computer-go@computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Seki frequencies

[Petri Pitkanen]

*"Seki means a constellation on the go board with two*

*living neighboring groups: one by Black, the other oneby White. Each of
the groups has only one eye"*

Why would you need an eye for seki?
http://senseis.xmp.net/?Seki
Shared liberties is good enough and quite typical in my limited experience

Petri

>
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Scraping lower-ranked games from kgs

[Petri Pitkanen]

Yes scraping for large amounts of data from  a smallish server is not
really polite. May overload the server. Besides quite inefficient. You
could make a request to owner of site instead. Assuming you can present
good enough reason  you might get lucky

2015-11-13 8:39 GMT+02:00 Josef Moudrik :

> Hello,
>
> I have a simple script for downloading info (gamelist, list of oponents,
> games) one by one here:
>
> http://repo.or.cz/gostyle.git/blob/HEAD:/kgs/kgs.py
>
> If you want to download more players, you need to search through opponents
> of players you know. But do not spam the kgs server too much please :-)
>
> Regards,
> Josef
>
>
> On Thu, Nov 12, 2015 at 2:35 PM Arthur Cater  wrote:
>
>> Hello,
>> I would be interested for research purposes in getting lots of game sgfs
>> of
>> lower-ranked players, to contrast with the high dan and pro games that
>> get put into collections. Even kyu games. I was thinking of getting them
>> from kgs archives.
>>
>> I wonder if anyone already has a script that could (or could be easily
>> adapted to) do this? And would they share?
>>
>> Thanks,
>>
>> Arthur
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Komi 6.5/7.5

[Petri Pitkanen]

Wrong kind of information if the issue is komi(or white win rate) vs
streng. EGD seems to have something but with grabby interface. So to get
any meaninfull data one would have request

Nothing as useful as chess-results
http://www.chess-results.com/tnr184639.aspx?lan=1&art=2&rd=1&wi=821 exists
where a relatively simple webspider could collect the information. It has
been done for players over 2000 and it shows that value of tempo increases
with players skill. Really no reason to doubt that in go. But no easy way
of getting the data exist.

KGS information would be useful but would need to be collected by the site
operator.  Webspider could overload the system and no interface exist that
would be usefull for collecting the data





2015-11-05 18:26 GMT+02:00 Michael Alford :

> On 11/5/15 7:19 AM, Petr Baudis wrote:
>
> On Thu, Nov 05, 2015 at 02:42:20PM +0200, Petri Pitkanen wrote:
>>
>
> I do doubt that there is sufficient data available on Go as it is not
>>> popular enough.
>>>
>>
>>How much data is enough?
>>
>
> May I suggest Remi's excellent goratings.org for data?
>
> Michael
>
> --
>
> http://en.wikipedia.org/wiki/Pale_Blue_Dot
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Komi 6.5/7.5

[Petri Pitkanen]

and in Go one move advantage need that your 1st pro-level mode works
together with your subsequent non-pro-moves

2015-11-05 14:55 GMT+02:00 Christoph Birk :

>
> On Nov 5, 2015, at 4:44 AM, Nick Wedd  wrote:
> > However, there's a powerful counterargument to the above  I can put the
> first black stone on the board as well as any professional can. And now,
> assuming I am playing an equally weak human, it's White who suffers most
> from the imperfection of our subsequent moves.
>
> But White already got the komi ….
> Christoph
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Komi 6.5/7.5

[Petri Pitkanen]

I do doubt that there is sufficient data available on Go as it is not
popular enough. But lets face it 7 points guaranteed profit is way easier
to utilize than initiative.

For chess it clearly visible quotation from wikipedia
"database between players with similar Elo ratings, commissioned by GM András
Adorján <https://en.wikipedia.org/wiki/Andr%C3%A1s_Adorj%C3%A1n>, showed
that as the players' ratings went up, the percentage of draws increased,
the proportion of decisive games that White won increased, and White's
overall winning percentage increased.[15]
<https://en.wikipedia.org/wiki/First-move_advantage_in_chess#cite_note-15> For
example, taking the highest and lowest of Adorján's rating categories of
1669 games played by the highest-rated players (Elo ratings 2700 and
above), White scored 55.7% overall (W26.5 D58.4 L15.2), whereas of
34,924 games played by the lowest-rated players (Elo ratings below 2100),
White scored 53.1% overall (W37.0 D32.1 L30.8)."
A clear difference and even the lowest category is pretty strong. Around
Elo 1500 1st move probably means next to nothing

Why would it be any different in Go? I think 1st move advantage is far less
for weak players Go than in chess, because doing a Null move is far  easier


2015-11-05 13:39 GMT+02:00 Petr Baudis :

> On Thu, Nov 05, 2015 at 09:03:38AM +0200, Petri Pitkanen wrote:
> > 2015-11-05 0:04 GMT+02:00 Hideki Kato :
> >
> > > The correct komi value assuming both players are perfect.  Or, black
> > > utilize his advantage (maybe in an early stage) perfectly.  Actual
> > > players, even strong pros, are not perfect and cannot fully utilize
> > > their advantages.  As a conclusion, white is favored.
> >
> > Let alone we do not have even sufficient understanding of perfect play to
> > say what is correct komi in absolute sense. Nor it is it even meaningful
> > concept. Correct komi is a komi that produces about 50/50 result.
> Obviously
> > komi that will result in 50/50 for professionals will probably favour
> white
> > in your average weekend tournaments. Just like in chess 1st move
> advantage
> > is clearly less meanigfull for weaker players than top professionals.
>
> I find the notion above really counterintuitive, personally.
>
> Do you have any statistical evidence for this?  I.e. increasing portions
> of white wins in even games as the player rating decreases?
>
> Petr Baudis
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Komi 6.5/7.5

[Petri Pitkanen]

Let alone we do not have even sufficient understanding of perfect play to
say what is correct komi in absolute sense. Nor it is it even meaningful
concept. Correct komi is a komi that produces about 50/50 result. Obviously
komi that will result in 50/50 for professionals will probably favour white
in your average weekend tournaments. Just like in chess 1st move advantage
is clearly less meanigfull for weaker players than top professionals.

So setting komi is not theroretical but statistical issue

2015-11-05 0:04 GMT+02:00 Hideki Kato :

> The correct komi value assuming both players are perfect.  Or, black
> utilize his advantage (maybe in an early stage) perfectly.  Actual
> players, even strong pros, are not perfect and cannot fully utilize
> their advantages.  As a conclusion, white is favored.
>
> Hideki
>
> Aja Huang:  2v52erc...@mail.gmail.com>:
> >Hi all,
> >
> >As you might know the Chinese professional player Ke Jie is like an
> >erupting volcano, triumphant in many domestic and international Go
> >competitions.
> >
> >In the interview at
> >
> >http://sports.sina.com.cn/go/2015-11-04/doc-ifxkhqea3033663.shtml
> >
> >Ke Jie said in his opinion on 19x19 komi 6.5 or 7.5 favors White. That
> >seems consistent to MCTS's behavior? i.e. on the empty board, with komi
> >7.5, Black's win rate is usually between 46% and 48% meaning White is
> >ahead. As the current top pro, Ke Jie's viewpoint is very interesting. :)
> >
> >Aja
> > inline file
> >___
> >Computer-go mailing list
> >Computer-go@computer-go.org
> >http://computer-go.org/mailman/listinfo/computer-go
> --
> Hideki Kato 
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Computer-go Digest, Vol 69, Issue 2

[Petri Pitkanen]

I think very few people here do not know message passing style of
programming.  I just not suited problem at hand. Not very cPU efficient.
This is high speed simulation anyways



2015-10-02 16:53 GMT+03:00 djhbrown . :

> .
> "sharing code is typically not going to be practical."
>
> that's not what i suggested.  perhaps someone else can explain the concept
> of message-passing distributed architecture better than me
>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] re comments on Life and Death

[Petri Pitkanen]

David said "estimate final score" which implies that all relevant things
are factored in, merely the unit of estimation is territory. Just like in
chess there are several things factored in - other than material - and all
are estimated as pawns.


I guess expert systems really are a dead  end in Go. Too many contradicting
heurestics

2015-09-09 10:31 GMT+03:00 Robert Jasiek :

> On 09.09.2015 07:42, David Fotland wrote:
>
>> I classify groups instead.  Each classification is treated differently
>> when estimating territory, when generating candidate moves, etc.
>>
>
> This is reasonable.
>
> The territory counts depend on the strength of the nearby groups.
>>
>
> Whether this is good depends on how you link strengths to counts.
>
> ***
>
> Was your influence function like radiated light? Such would have too
> little meaning.
>
> Monte Carlo has a big advantage in that it estimates the probability of
>> winning the game, rather than my old approach of trying to estimate the
>> final score.
>>
>
> Whether it is an advantage depends on one's objectives.
>
> For an expert system, estimating the score is just one aspect for further
> application and does not finish the job. (To start with, a positional
> judgement consists of more than the 'territory count' and group strengths
> of the current position.)
>
>
> --
> robert jasiek
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] OT (maybe): Arimaa bot notably stronger

[Petri Pitkanen]

I played  few games against bots in arimaa.com and they seemed to react.  I
think the eval can be used for that?

I did not find the game interesting. Just being hard for computers does not
make it fun. So I quit playing after few games

Petri

2015-04-23 18:32 GMT+03:00 Stefan Kaitschick :

> The funny thing is, that in computer go there are no goals, except winning.
> And therefore, the reason for a win cannot be determined.
> One crude measure might be to use "stronger" attacking moves in the
> playouts, when the winrate is low.
>
> unrelated:
> Does anyone know if the successful Arimaa bot "responds" to the gold setup
> when it's silver, or if it just ignores how gold deployed?
> Just wondering.
>
> Stefan
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] fast + good RNG

[Petri Pitkanen]

Assuming you are using some sensible OS there better ways profile than
sample like oprofile for linux. There is similar thing for FreeBSD I
think.  No instrumentation san sampling gets automated

Petri

2015-03-30 8:05 GMT+03:00 hughperkins2 :

> 40% sounds pretty high. Are you sure its not an artefact of your profiling
> implementation?
>
> I prefer not to instrument, but to sample stack traces. You can do this
> using gdb by pressing ctrl-c, then type bt. Do this 10 times, and look for
> the parts of the stack that occur often.
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [computer-go] one more look at the scoring function

[Petri Pitkanen]

They also all lose games on endgame same manner. Having won a game by 30 pts
they start giving away those points for - sometimes - imaginary safety,
allowing other player to come within striking distance. Some sort dynamic
komi would be nice  in endgame, but would probably not work.

In Handicaps I think pachi has dynamic komi.

Petri

2009/12/20 Stefan Kaitschick 

>  Looking at the games on kgs, both ManyFaces and Zen are pretty decent at
> giving handicap, but still fairly weak at taking handicap.
> I think the problem remains, that they allow the opponent to close the gap
> too easily. Once the game is close they get much stronger,
> but by then they are in a real danger of losing. I feel the problem is
> still with the scoring function. Watching them give away points with
> both hands, I have advocated a dynamic negative komi, thereby almost
> starting a flamewar on this list. So as not to start it again, let me state
> here that I now think that it's a remedy of dubious value, making the bots
> play more "positive" moves that look better, but might hurt the bots chances
> of winning by going head to head with a stronger opponent.
> Here's my new suggestion: how about trying to map the score to the chances
> of winning?
> In the later endgame, a putative 0.5 point win might be something like 90%,
> a putative 1.5 point win 95%.
> Early in the game that would be maybe 51% and 53%.
> I'm not sure of what the most useful numbers would be ofcourse, or how
> quickly they would change, or if there should be other factors than the move
> number.
>
> Stefan
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Live broadcasting at UEC Cup

[Petri Pitkanen]

2009/12/1 Rémi Coulom 

> David Fotland wrote:
>
>> I'd like to thank all of the people who organized the UEC tournament for
>> providing machines and operators to allow Many Faces and others to
>> participate.  I'd like to suggest that the UEC organizers consider using a
>> Swiss tournament system in the future since it gives a more accurate
>> assessment of program strength.
>>
>> Regards,
>>
>> David Fotland
>>
>
> Hi,
>
>
> I like the direct-elimination system, because it determines a clear winner
> in a deterministic number of rounds. I don't like the KGS system, where the
> winner is determined by SOS.
>
> Rémi
>

Determining clear winner is good. But clear winner does not mean finding
best player, obviously. Swiss system fails to find clear winner in cases
where the superiority is not clear, which is kinda correct.

CUP's are usually used in backgammon tournaments, but there the goal is not
to find who is the best player but who collects the prize money. So in case
there in monetary awards CUP's are good. Otherwise Swiss system is better.

Petri
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Hahn system tournament and MC bots

[Petri Pitkanen]

Well No, this games game lot harder. Even when point matter, 1st goal is to
win the game in traditional sense to get any points at all. Which make just
as hard as normal game. Then comes huge risk assesment risks involved. Lets
assume - not so rare case - that you can go for the throat or attack mildly
to secure some points. In Normal go most players - if they are willing to
use the time - can make score estimate with 10 pt accuracy and use that as a
guidance. In Hahn go the assessment comes lot harder and involves fuzzy
variables that are hard to estimate by computer or human as well. But this
is exactly kind of thing where human reasoning can give good results.

Petri

2009/11/23 Don Dailey 

> I am estimating that this is a simpler game but I could be wrong.   I think
> simpler games favor computers.I think it's simpler because I am a weak
> player and I think more in terms of  total points rather than winning games
> (in my beginners mind there is no difference even though objectively I know
> better, but it's too much for me to process.) Even strong players do
> this as a shortcut to make it "easier" to think about their next move,  but
> they are more aware of concepts like,  "I MUST win this chunk of the board
> or I will lose the game."
>
> So it seems pretty evident to me that this is a simpler concept to grasp
> and play by and thus one that computers would do better at relative to good
> human players who are much better at risk assessment than computers.
>
> I won't go so far as to say that this eliminates the element of risk from
> the game,  but it seems obvious to me that it is an easier way to think
> about the game.
>
>
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Joseki Book

[Petri Pitkanen]

Only papers I can recall are from seventies (assuming you mean academic
papers) from Wilcoxx. I may have electrical copies. Not sure though. I
managed to find some of them from ACM site.

That paper described  position based approach where each and every stage was
stored into datastructure, kinda like huge pattern matching library. Was
called lenses if I remember correctly. More common way is store joseki moves
as a tree.

Biggest issue is always hos key in all those variations.

Petri

2009/11/9 Jessica Mullins 

> Hi,
>
> I am wondering what is the best way to build a Joseki Book? I am a student
> at
> Lewis & Clark College and am working with Professor Peter Drake to build a
> Joseki Book for the program Orego.sed aproach i.e each state of joske
>
> Right now I am extracting moves from professor players and saving those
> into a
> database. Then if during game play a position is contained in the database,
> play the response move like the professional. I am just wondering what
> other
> people have done to build a Joseki Book, or if anyone knows of any papers
> that
> might be helpful.
>
> Thank you,
> Jessica Mullins
> Lewis & Clark College '10
>
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [SPAM] Re: [computer-go] Re: First ever win of a computer against a pro 9P as black (game of Go, 9x9).

[Petri Pitkanen]

I cant recall any offocoal challenges. I do remember some such statement in
some other challenge, but failed to google it up.

Human computer chess challenges are not likely to happen anymore. What would
be the point for human? Hydra could probably beat anyone. And as processors
get faster any of top 10 programs in top commercial hardware and beat just
about anyone. Why would anyone sponsor such an event.

Corresponce chess has also suffered as everyone has access to computers and
it pretty hard to prevent cheating.

Petri


2009/10/30 Olivier Teytaud 

>
>
>>
>> I think in correpondence chess humans still hold against computers
>>
>> Petri
>>
>
> Are there sometimes games organized like that ? This is really impressive
> to me.
>
> (maybe MCTS might win against alpha-beta in chess with huge time settings
> :-) )
>
>
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Re: First ever win of a computer against a pro 9P as black (game of Go, 9x9).

[Petri Pitkanen]

On anecdotal evidence:

Manyfaces on ""medium" time settings KGS = 2k (accounts  manyfaces and
manyfaces2)
Manyfaces1 playing round 10 sec/move is able maintain 1d rank.

So by reducing oppponents thinking time bot gets relative advantage of
3stones.

Also in chess it is uusually considered that humans gain more for longer
thinking times. In blitz games chess computer have won worl champion long
before in normal thiking times.

Some people are more able than others to make move in few seconds, while it
is pretty hard for the most.

So yes computer do get better with longer thinking times but so do most of
the human opponents. Comparing to pro's does not make sense currently as
they still have rather superior skill compared to bots. Esspecially their
tactical skill are way beyond, allowing them to play with just few seconds
per move.

And this is quite logical. Easier to see in chess. Game tree grows by factor
of 36 on each ply so bot thatis not too smart doubling thinking times will
gain a little but narrow searcher like human will gain a lot.

I think in correpondence chess humans still hold against computers


Petri

2009/10/29 Don Dailey 

> There is no question that computers play better at longer time controls
> even though this has been disputed on this group.   Is there any issues with
> parallelism at short searches?In the "old days" when I competed in
> computer chess with many processors,   the program could out-search the
> single processor version many times over at long enough time controls,  but
> the first few ply of search were quite a bit slower,  so I would have been
> better off using 1 CPU for speed chess games.
>
> What this meant of course is that at long time controls the CPU advantage
> for the computer was exaggerated and it may have even been the case that a
> human had a better chance at fast time controls in order to suppress the big
> advantage of all those CPU's.I probably could have tuned some of this
> effect away but we were not competing at short time controls.
>
> Is there anything like that going on?
>
> - Don
>
>
>
> 2009/10/29 Olivier Teytaud 
>
>> Some elements around blitz:
>>
>>
>> - My feeling that blitz games are harder for computers is based on our
>> games
>> against humans: we always lost games with short time settings. Even in
>> 9x9,
>> Motoki Noguchi or Pierre Audouard could win plenty of fast games,
>> whilst
>> playing strange openings for fun. This is for sure on a small sample.
>>
>> - The newspapers don't take into account or even report the difference
>> between
>>blitz games and standard games on the 29th of october, and they use the
>> not
>>very relevant complexity comparisons based on the number of possible
>> boards
>>or games. But they have nice photos for promoting computer-go :-)
>>
>> Best regards,
>> Olivier
>>
>>
>> Dear all (in particular for your question, Hideki!), please find enclosed
>>> some newspapers about the games played on October 29th. Most of them are in
>>> chinese.
>>>
>>> I don't read chinese, if some people can extract some elements... I'll
>>> try to have some translations here with our chinese students.
>>>
>>> Best regards,
>>> Olivier
>>>
>>>
>>
>>
>> --
>> =
>> Olivier Teytaud (TAO-inria) olivier.teyt...@inria.fr
>> Tel (33)169154231 / Fax (33)169156586
>> Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS - Universite Paris-Sud),
>> bat 490 Universite Paris-Sud 91405 Orsay Cedex France
>> (one of the 56.5 % of french who did not vote for Sarkozy in 2007)
>>
>>
>>
>> ___
>> computer-go mailing list
>> computer-go@computer-go.org
>> http://www.computer-go.org/mailman/listinfo/computer-go/
>>
>
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] MC hard positions for MCTS

[Petri Pitkanen]

That is well known fact of go, that usually defence is easier. But evidence
is anecdotal.  Getting real evidence from real games cannot be automated as
all concept involved are rather vague and difficult to classify. Hence I am
willing to accept such information as passed on to me in books like "defence
and attack"

Petri

2009/10/27 Darren Cook 

> > But the biggest problem is that the path to life/ko is very narrow.
> > The defender has many useful moves and the invader has few.
> > So MCTS will falsely judge invadable areas to be safe.
>
> Interesting, I'd not thought about it in that respect: I know I can soon
> find positions where the defender has only one way to defend but the
> attacker has many choices.
>
> But, has anyone gathered stats on positions, from real games, that
> require precise play by the defender/attacker/both/neither? Is defending
> really easier than attacking?
>
> Darren
>
>
> --
> Darren Cook, Software Researcher/Developer
> http://dcook.org/gobet/  (Shodan Go Bet - who will win?)
> http://dcook.org/mlsn/ (Multilingual open source semantic network)
> http://dcook.org/work/ (About me and my work)
> http://dcook.org/blogs.html (My blogs and articles)
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

[computer-go] MC hard positions for MCTS

[Petri Pitkanen]

Hello,

Are there more peculiar situation that will cause problems for MCTS apart
from the three I know.
1. Nakade (this is partuially solved in most of the programs)
2. Semeais
3. Double Ko.

Last one was new to me. See
http://files.gokgs.com/games/2009/10/26/ManyFaces-Hyoga.sgf

In that game manyfaces wastes ko-threats in hopeless ko in lower left
corner. And wins game by human weakness of pushing with stones taht are
short of liberties.

Is there any nice way to solve this or shouldd all of these solved in
expanding the node using "classical" go-AI-engine.

Petri

-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Handicap games collection?

[Petri Pitkanen]

I dont have but harvesting those from KSG archives should not be too
difficult using Pelr/mechanize or similar system. Remembering to put sleeps
into scripts as not to overload the system. Start f.ex by getting the list
of 100 player and see through their games.

Petri
2009/10/20 Petr Baudis 

>  Hi!
>
>  Does anyone know of any handicap games collection? For MCTS handicap
> play research, I'm looking for at least 500 games of any handicap (1-9),
> ideally of reasonable strength (KGS 2k-9d).
>
>  Thanks!
>
> --
>Petr "Pasky" Baudis
> A lot of people have my books on their bookshelves.
> That's the problem, they need to read them. -- Don Knuth
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Great Wall Opening by Bruce Wilcox

[Petri Pitkanen]

Not really a compuetr Go issue, but I do not think that great wall is
superior even when completed. It is not too bad but it needs a definite
strategy from wall owner. I.e building side moyos using wall as a roof and
hoping that the other guy gets nervous and jumps in. So by being patient is
pretty good defence against it.

But to computer go: It may well that MCTS programs have abilities that match
the great wall fuseki. They do like moyo's and fighting so this sound like a
god match, but i doubt that it gives any meaninful boost. Just fun for a
change.

Petri

2009/10/20 

>  I heard about a pro comment that the Great wall and similar openings are
> quite feasible, but also quite easily thwarted. If you opponent plays it,
> you just prevent him from completing it by taking the last point yourself.
> This should give him an inferior position. If you let him complete it, he
> probably has a superior position.
>
> Dave
>
>
> --
> *Van:* computer-go-boun...@computer-go.org namens "Ingo Althöfer"
> *Verzonden:* vr 16-10-2009 20:55
> *Aan:* computer-go@computer-go.org
> *Onderwerp:* [computer-go] Great Wall Opening by Bruce Wilcox
>
>  In the year 2000 I bought the book
> "EZ-GO: Oriental Strategy in a Nutshell",
> by Bruce and Sue Wilcox. Ki Press; 1996.
>
> I can only recommend it for the many fresh ideas.
> A few days ago I found time again to read in it.
>
> This time I was impressed by Bruce Wilcox's strange
> opening "Great Wall", where Black starts with a loose
> wall made of 5 stones, spanning over the whole board.
>
> Bruce proposes to play this setup as a surprise weapon,
> even against stronger opponents.
>
> Now I made some autoplay tests, starting from the end position
> given in the appendix of this mail.
> * one game with Leela 3.16; Black won.
> * four games with MFoG 12.016; two wins each for Black and White.
> So there is some indiciation that the Great Wall works even
> for bots, who are not affected by psychology.
>
> I would like to know how other bots perform in autoplay
> after this opening.
>
> Cheers, Ingo.
>
>
> --
> GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
> Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Neural networks

[Petri Pitkanen]

Neural network tend to work well in those cases where evaluation function is
smooth, like backgammon. Even inbackgammon neural networks do give good
results if situation has possibility of sudden equity changes like deep
backgames and deep anchor games. Top backgammon programs 3-ply search on top
neural network to handle these problems.

I do not know wher neural nets would fit well, perhaps finding invasion
spots?

There has been something on chess neural nets so maybe checking what they
have done?

I am pretty sure there was neural net program in later 80ies?

Petri

2009/10/14 Petr Baudis 

>  Hi!
>
>  Is there some "high-level reason" hypothesised about why there are
> no successful programs using neural networks in Go?
>
>  I'd also like to ask if someone has a research tip for some
> interesting Go sub-problem that could make for a nice beginner neural
> networks project.
>
>  Thanks,
>
> --
>Petr "Pasky" Baudis
> A lot of people have my books on their bookshelves.
> That's the problem, they need to read them. -- Don Knuth
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Rating variability on CGOS

[Petri Pitkanen]

All rating model assume tha If A cab B B easily and B can beat C easily then
A can beat C easily as well. As we all know this is ususally true but no
always.  I know I cannot handle AyaMC in KGS although rating of KgS indicate
that I should be favorite. I assume that these sort wrong skill set against
C problems could be a big part of explanation.
Petri

2009/10/9 Brian Sheppard 

> >One must be very careful about proclaiming wild transitivity issues.  I'm
> >not saying it's not an issue, there is some going on with every program on
> >CGOS, but with less than 500 games between any two players you are going
> >to get error margins of +/- 30-50 ELO or something like that.
>
> Actually we are certain that significant differences are being observed. If
> we pool the Pachi and Pebbles data, then the null hypothesis is that
> Valkyria defeats both programs by 79%. The observed data differs by at
> least
> 3.5 standard deviations.
>
> Note that we are talking about 150 rating points.
>
>
>
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Dynamic komi at high handicaps

[Petri Pitkanen]

Maybe they are long way from giving handicaps to you. But best of bots
in KGS are around 2k and there are hundreds of  9k and weaker players
present there at all times. So being able to play white is worthy
thing at least for commercial bot.

Petri

2009/8/13 Christoph Birk :
>
> On Aug 12, 2009, at 2:51 PM, Don Dailey wrote:
>>
>> I disagree.   I think strong players have a sense of what kind of mistakes
>> to expect, and try to provoke those mistakes.   Dynamic komi does not model
>> that.
>>
>> It also does the opposite of making the program play provocatively, which
>> I believe is necessary to beat a weaker player with a large handicap against
>> you.    Instead of making it fight,  it encourages the program to be content
>> with less.   How does this model strong handicap players?
>
> Maybe dynamic komi works better for BLACK? Computers are still
> a looong way from actually _giving_ a handicap.
>
> Christoph
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Roadmap 2020 - using analysis mode to improve programs

[Petri Pitkanen]

2009/4/23 terry mcintyre :
> Programs which get semeai and seki right every time might be a few stones
> stronger. They'd certainly be more valuable as teaching tools. In the game
> above, a stronger program would have exploited my earlier weakness; this
> would have encouraged me to make better moves.
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/

Actually not. It seems so to a human who every now and then avoids
loss by being better at these. But close semeais are rare. Sekis are
rarer and program do not fail on theses every time. Go is a game where
you can excel by making steady progress throughout the game without
any brilliant moves. Also it is quite okay to compensate with other
skill, I just played Mogo in KGS  and got slaughtered after a careless
cut. Well Killing and almost killing a group is where MC programs
excel (relative to their strength) and those situations occur in
almost every game..

I think semeai problem is easier to solve with:
 - Preanalysis by a "classical" go-algorithm. To my understanding this
is what MFOG does
 - When we have even more CPU we can have even heavier playouts. Still
an open issue whether smarter playout or more playouts is way to go.
Although as I remember there were some mailing were it was mentioned
cases where a smart playout could even hurt.



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Libego benchmarking

[Petri Pitkanen]

Because your time measurement has gone wrong. You get 0 seconds in
time hence kpssa in infinity.

Petri

2009/4/23 Michael Williams :
> Here is my full set of numbers.  I wonder why the known kpps/GHz but unknown
> kpps.
>
>
>
> = Benchmarking, please wait ...
>
> = 20 playouts in 0 seconds
> 1.#INF kpps
> 40.0245 kpps/GHz (clock independent)
> 105316/94359 (black wins / white wins)
-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Fast ways to evaluate program strength.

[Petri Pitkanen]

2009/4/8 Zhiheng Zheng :
> I think most of test are designed by people  who is stronger than best
> computer go program. So if MC program fail to pass a test, it is most likely
> MC is wrong.  MC program is strong in some aspect, but week in other aspect.
> And the test suit is too focus on special aspect. We might split the test
> into different category, like opening, end game, L&D etc, and for each
> category we can set different weight. And when program pass all test, we can
> calculate final score adjusted by weight.
>
> ZZ
>

Sure program would be "wrong" but it does not imply weak. It is easily
a case that program A would fail on tests  and program B would do
great on those, but on actual game program A would wipe the carpet
with program B.

I think L&D id kinda showcase for this. Early MC programs had huge
issues with it but they were still pretty strong. And their opening
... did not even resemble opening of humans. But still they are/were
pretty strong.

Passing test is nice, but it matters only if it REALLY translates to
winning games. So I am afraid that for a while playing few hundred
games is the only meaningful measurement available.

End game is another issue. MC programs only aim on winning, so they
endgame is nor perfect in sense human would define it, but perfect
enough to win if the game is winnable.

Petri

-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Fast ways to evaluate program strength.

[Petri Pitkanen]

This is nice idea and  this is to a degree what GnuGo regression test
does. But as there is more than one way to skin the cat, it will not
capture true strength of the programs. If you put Mogo to solve the
tests from a book for example 501 opening problems, it will probably
fail minimum of 75% of them because it has completely different style
from what is expected from humans. This will also lead to different
solution in connecting and capturing. MC program may reach the
conclusion that it best option to ignore the whole connection issue.
They often do exactly that.

Petri



2009/4/8 Zhiheng Zheng :
> I have some ideas.
>
> When I learned go, I saw some small go books with many test suits for Life
> and Death, Connect etc. And each test have 4 candidate moves, each move has
> a score, best is 10 2nd is 6 3nd is 3 and the worst one is 0. After I finish
> a test, I will go a score. And a range of score is mapped to a level like 1d
> or 3d etc. Maybe we can gather these test suits from existed go books, and
> run tests on our program , then we can know how strong it is.
>
> Another idea is more automatical one. Every computer go program has its own
> regression test suit. We can gather them togather, and let different existed
> programs  to run the tests. And we can use our own program to run the test,
> and compare our results to exsited programs results, then we can know if our
> program is stronger or weaker than the existed programs.
>
> Zhiheng Zheng
>
>
>
> 2009/4/8 terry mcintyre 
>>
>> Amen to that. When using positions to judge the strength of a program, one
>> would need to test not just one "pro move", but a sequence of plays --
>> including some which don't appear in pro games. A pro knows how to deal
>> decisively not only with the optimal plays of other pros, but also with
>> suboptimal plays from the rest of us. Programs are often even stranger than
>> human players.
>> If I were designing a test set, I'd ask pros to defeat the program, and
>> would convert the blunders into a test set. To improve, the program would
>> have to generalize the lessons learned from those test cases.
>>
>> Terry McIntyre 
>>
>> -- People never lie so much as after a hunt, during a war or before an
>> election. -
>> Otto von Bismarck
>>
>> 
>> From: steve uurtamo 
>> To: computer-go 
>> Sent: Tuesday, April 7, 2009 5:12:27 PM
>> Subject: Re: [computer-go] Fast ways to evaluate program strength.
>>
>> otherwise pair-go wouldn't be as funny to watch.
>>
>> s.
>>
>> On Tue, Apr 7, 2009 at 8:05 PM, Michael Williams
>>  wrote:
>> > Łukasz Lew wrote:
>> >>
>> >> I would like to rephrase my question:
>> >> Let's measure prediction of pro moves of a whole engine while
>> >> modifying heavy playouts / MCTS in the engine.
>> >> How well might it work?
>> >
>> > Probably not well.  Because what matters is not how often you play
>> > strong
>> > moves, but how often you avoid blunders.
>> >
>> > ___
>> > computer-go mailing list
>> > computer-go@computer-go.org
>> > http://www.computer-go.org/mailman/listinfo/computer-go/
>> >
>> ___
>> computer-go mailing list
>> computer-go@computer-go.org
>> http://www.computer-go.org/mailman/listinfo/computer-go/
>>
>>
>> ___
>> computer-go mailing list
>> computer-go@computer-go.org
>> http://www.computer-go.org/mailman/listinfo/computer-go/
>
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Published source for mercy rule?

[Petri Pitkanen]

Libego has one type of mercy rule.

Petri

2009/2/27 Seth Pellegrino :
> Hello list,
>
> I've managed to track the idea of a mercy rule in monte-carlo playouts back
> to a mail sent to this list by David Hillis:
>
> http://computer-go.org/pipermail/computer-go/2006-December/007478.html
>
> I'm currently putting the finishing touches on a paper which includes this
> idea, and I was wondering if anyone knew of any published sources where I
> could cite the idea?
>
> Thanks,
>
> Seth Pellegrino
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: petri.t.pitka...@gmail.com
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Selling a computer go program

[Petri Pitkanen]

Commercial market for Go software is in Japan in Korea. Western player
do not make significant numbers and Chinese probably find bettre uses
for money - although there more reach Chinese people than people in
Finland.

Petri

2008/11/21 Michael Gherrity <[EMAIL PROTECTED]>:
> Hi,
>
> I have read that the amount of money that a winning computer go program
> would make in a go tournament is insignificant compared to the amount of
> money that such a program would earn selling to the general public. I have
> also read that the biggest pirates of computer software come from Germany,
> the UK, and the US. The foreign exchange student we are hosting from Beijing
> China said that most people in China do not buy software, but download it
> for free off the net.
>
> So what is true?
>
> mike



-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Kaori-Crazystone

[Petri Pitkanen]

2008/9/4 Rémi Coulom <[EMAIL PROTECTED]>:
> only 5k, so I cannot really tell. But when I see the horrors it plays in
> some games, I suppose it must play much stronger than 1k in some other games
> in order to get a rating of 1k.
>
> Look for instance at these two games:
> a win: http://files.gokgs.com/games/2008/8/23/CrazyStone-mandelbrot.sgf
> a loss: http://files.gokgs.com/games/2008/8/23/CrazyStone-beoren.sgf
> (with comments of the opponents at the end)
>
It also shows that some people lose just because they assume that they
can outsmart the bot in any fight regardless how unfavourable is the
start of the fight. Looking these games where humans pull surprise
wins you can often see that they just don't fight for the joy of it
but only when they have some backing.

Leela especially has aggressive style for which opponent getting
carried away by it is pretty easy. And losing those fights is easy as
well.

But as for Semeai problem I think one would need pre-analysis of
situation, in classical program fashion and recognising important
semeias and the directing the search with specialized move generators
for semeai. I guess the term would be importance sampling.

-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] What Do You Need Most?

[Petri Pitkanen]

Well MC-UCT programs (Mogo, CrazyStone and many others) need more CPU.
Doubling the CPU  gives a constant raise in playing level. There are
even some threads about the issue. But becoming -say -  6 stones
stronger I guess they would need more then 2^6 times more CPU. Also
there could be a corner point for current algorithms- so maybe they
need new playout algorithms in future?

Traditional programs may not even gain on CPU alone (GnuGo, ManyFaces
of Go, GO++). Depends on actual implementation. But for example GnuGo
would hardly be any stronger with more CPU. So it would need new
algorithms and more "expert" rules.

2008/7/28 Darren Cook <[EMAIL PROTECTED]>:
> My question isn't about how strong programs are now, or what is the
> definition of a dan, or what you think will happen in the future. The
> question is: what do you need to give your current 19x19 program another
> 6-ish ranks in strength (or 6+N where N is the distance between your
> program and the top programs).
>
> Darren
>
>
> --
> Darren Cook, Software Researcher/Developer
> http://dcook.org/mlsn/ (English-Japanese-German-Chinese-Arabic
>open source dictionary/semantic network)
> http://dcook.org/work/ (About me and my work)
> http://darrendev.blogspot.com/ (blog on php, flash, i18n, linux, ...)
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>



-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] What Do You Need Most?

[Petri Pitkanen]

2008/7/28 David Fotland <[EMAIL PROTECTED]>:
> The traditional programs are around 10 kyu, but the new ones are 2 to 4 kyu,
> at least on KGS.  I've seen some handicap games against dan players that are
> consistent with these ratings.
>
> It wouldn't surprise me to see 1 dan from an MC program before 2010, running
> on an 8 processor mainstream system.
>
> David
>

Here is a big catch for setting goals. 3-dan by which
organization/server/whatever. At what point of time? KGS has gone
through mane abrupt ratings changes and and I don't see any reason why
it would not go through such a thing in future as well. Currently 2k
KGS is about 5k EGF. So best of MC programs would still need about 7-9
stones handicap from European 3-dan (which is not well defined
strength either). That is about 700-1000 Elo-points and if we assume
100 elo gain  for a doubling of CPU power .

So 1D KGS within year or two
 1D EGF   I doubt if that happen within 5 years, But if thre is a
new innovation on par with MC_UCT. Then maybe.

-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] manyfaces on KGS

[Petri Pitkanen]

Is the KGS manyfacesofgo MC version or traditional. Just seems to
tenuki quite MC fashion

Petri Pitkänen


-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] My experience with Linux

[Petri Pitkanen]

2008/4/9, Don Dailey <[EMAIL PROTECTED]>:
>
>
>  >
>  > Since I sell software, building Linux apps is out of the question, since
>  > Linux users will insist that  I give them my work for free.
>  >
>  I don't have any issue whatsoever with making money by selling software
>  either.   I'm not one of those guys that think this is somehow
>  immoral. I don't believe most Linux users think this either.
>
Some of linux people think so but then again those individuals will
not even steal your product as they use only free software and very
strict on what licenses mean. But SW market on Linux is pretty  -
other than professionalk SW likeHW  simulators etc.- small so I guess
making only for windows if better option . Unless you develop on
something likee QT which is fairly portable.

-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

[computer-go] CGos 19 cannot view game records

[Petri Pitkanen]

Is just my problem or do others have it. When I try to download for example:
http://www.lri.fr/~teytaud/SGF/2008/01/30/17067.sgf
I Get 403 response with following line:
You don't have permission to access /~teytaud/SGF/2008/01/30/17067.sgf
on this server.

Cheers,
Petri
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] 19x19 Study - prior in bayeselo, and KGS study

[Petri Pitkanen]

2008/1/30, Don Dailey <[EMAIL PROTECTED]>:
> It would get it eventually, which means this doesn't inhibit scalability.

>
> Having said that,  I am interested in this.  Is there something that
> totally prevents the program from EVER seeing the best move?I don't
> mean something that takes a long time,  I mean something that has the
> theoretical property that it's impossible to every find the best move,
> even given eternity?
>
> - Don
>
> Gian-Carlo Pascutto wrote:
> > Don Dailey wrote:
> >
> >> So I think this is nakade.
> >
> > Yes. Leela 0.2.x would get it wrong [1].
> >
> > [1] Not eternally, but it would still take unreasonably long.
> >

Eternity is a long time. So I think UCT program would eventually find.
But compared to ProofNumber, AplhaBeta reader with at least 100-fold
CPU usage. To estimate how far UCT sees lets take 1000 000 simulation.
Typical middlegame simulation with no prior pruning there should be
about 200 possible moves. And about 200 possible answers. Since it is
gona spend at least on esimulation on every first level move an
probably attempt asme on second level. There is not much left 3-ply is
there? Considering the fact that wopuld 400 000  prior simulation from
which start expanding the tree. And it is quite unlikely that nakade
key point would have strong UCT value anyway.

5-point nakade is something that shows up frequently and that takes
more 3-deep lookahead to know. Or simple pattern mathcer and knowledge
that surrounding grou pa has more eyes. Even worse situation for UCT
program would a 5 pout nakade in close semeai with outside group.
Unless there heurestics etc it would never get it right. If my memore
serves AyaMC was using tactical search to prune moves from UCT?

I have first hand experience on this. It wasn't anything complex like
nakade but simply a situation where Crazy Stone tought that it had 60%
chance of winning for about 20 moves when it has excactly 0% chance.
Just that the dead group had three liberties and the outside group had
about 5 ==> UCT three never gets deep enough see that it dead as door
nail. Nice feature by the way this CrazyStone rankbot has on the KGS
that you can ask on chat its' estimate.

Yes eventually it will get deep enough. But I think some sort of
tactical analysis will get there first. Just mixing these two is
somewhat difficult
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

[computer-go] LIBEGo optimum parameters

[Petri Pitkanen]

Hello,

Has anyone experimented with libego parameters? What would be
reasonable starting point on configurations on 19x19 board? I am
considering using GnuGo to give the moves MC is allowed to simulate
for first couple of plies in simulation and then pure random. Just to
see if it makes any sense at all.

I would try the 3x3 patters but that is probably very tedious effort :(.

Petri
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Is MC-UCT really scalable against humans?

[Petri Pitkanen]

2008/1/22, Erik van der Werf <[EMAIL PROTECTED]>:
> In the future, when humans are consistently defeated by computers on
> 19x19 and the remaining players move up to a more 'interesting' size,
> will you be claiming that 19x19 isn't Go either?
>
> E.

Maybe I will, but 17x17 is quite like 19x19, While 9x9 is completely
different game. I do not like to play nor does feel like the same. It
is more of a teaching method for newcomers. Skill obtained on 9x9 are
transferred to larger board but they are still just an small subset of
skills needed on full sized board.
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Is MC-UCT really scalable against humans?

[Petri Pitkanen]

2008/1/22, Alain Baeckeroot <[EMAIL PROTECTED]>:
> This is not a bug, its a feature of MC program.
> It seems you really know very little about their logic and strenght.
> Try on 9X9 and you will see they are very strong at tactics.
I know their logic. Just it fails on 19x19 board on some little cases.
9x9 is not Go, so it does not matter what they achieve in that.

>
> They play to maximize winning probability, not score. So if an
But in these cases PWin =0 about. Just that program failed to see it
untill its' dead groups was down to two liberties. Yes it is not an
bug. It is too few simulations issue. question is how many more of
these are needed before it could see it.

>
> On 19x19 they play cosmic style, and are strong at sacrifice. add some
> handicap if you are stronger , they are good oponent.
>

Sure on those they some times excel. Although not on early phases of the game.
> Alain
>

Petri
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Is MC-UCT really scalable against humans?

[Petri Pitkanen]

2008/1/22, Eric Boesch <[EMAIL PROTECTED]>:
> On Jan 22, 2008 1:43 AM, Petri Pitkanen <[EMAIL PROTECTED]> wrote:
> > Even top MC programs fail to see  that a group with 3 liberties with
> > no eyes is dead.
>
> A 3-liberty group with no eyes has a 100% chance to die during
> playouts unless a surrounding group dies first. 100% chance to die is
> as good a job of "seeing" deadness as a generic MC playout can ever
> do.
>

But As I played these programs they have a completely lost game. A
3-lib group against a group with so many liberties that i did not
bother to count and it did not resign. Until I got tired of it and
removed a liberty. After that it managed to simulate yje game as
hopelessly lost and resigned . This was crazy stones if memeory
serves. Similar thing have happened with other programs.

It also leads them to losing semeais because take may take a move in
other part of board  when they cannot afford it. Assuming that group
entangled in fight have 3 liberties or more. Which is one trick to win
them "unfairly"

-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

[computer-go] Is MC-UCT really scalable against humans?

[Petri Pitkanen]

So far I played these MC programs at it seems they are doing well
against humans mostly because the moves they play are bizarre and some
times throw unreasonable contact fight challenges. They win more often
than they deserve just because many weak players (like KGS 4k level
players are) quite often panic and start making ever funnier moves
than they do usually.

Point is that being tactically challenged is rather common amongst
weaker players but as get to higher ranks it gets rather rare quality.
And MC programs simply suck tactically and adding more simulations
gives very little gain for amount of CPU spent. The full board usage
may getter better faster.

Even top MC programs fail to see  that a group with 3 liberties with
no eyes is dead. So by doubling the simulations it would now fail on 4
liberties instead of 3?  How many fold the simulation count would have
to understand 2-eye concept? I am pretty sure that 32 fold increase
will not do that, but obviously there is amount of doublings that will
do the trick. Question is will that happen on our lifetimes. Or will
the next generation be some sort of hybrid approach?

Petri
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] How does MC do with ladders?

[Petri Pitkanen]

2007/12/11, Don Dailey <[EMAIL PROTECTED]>:
> Hi Petri,
>
> I happen to think that MC is the most human like approach currently
> being tried

Ye in sense Alpha-Beta is human like. It one feature we do and takes
it to extreme. And using different method of evaluation.
.
>
> The reason I say that is that humans DO estimate their winning chances
> and "tally" methods, where you simply tally up features/weights
> (regardless of how sophisticated)  is not how strong humans think about
> the game.
>
Tallying up ius the non-human part. Extracting features and assigning
meaning to them is very human. Good go player describe moves they make
with terms like thicknes, wall, spere of influence,invasion.
Obviously these are not needed if one searches deep enough but how
deep that would be?

> game too.We may notice 3 moves that look playable, but gradually
> come to focus on just 2 of those.   Essentially monte carlo does this
> too.Very narrow focused trees.
Here we completely agree. It just picks the moves with different
emphasis. And we do tactical analysis all the time. Something MC
program is pretty weak at. I for instance played MOGO and it refused
to resign until I places a dead group in atari. Any 20 would have seen
that specific situation. Still that same 20 would have lost the game
easily. So this is very unlike humans
>
> I attribute the success of MC to the fact that it's the best simulation
> of how WE do it.The other approaches are clearly more synthetic,
> including raw MC without a proper tree.
>
It could be the best but it is not very close. And adding more go
knowledge to it may make it weaker by consuming CPU. There must be a
third way. But this is the best idea that has posppoed up in years -
or more like a decade

> - Don
>
Petri
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] How does MC do with ladders?

[Petri Pitkanen]

2007/12/11, terry mcintyre <[EMAIL PROTECTED]>:
> With Go, there are many situations which can be read out precisely, provided
> that one has the proper tools - ladders, the ability to distinguish between
> one and two eyes; the ability to reduce eyespaces to a single eye with an
> appropriate placement; and so forth. Failure to recognize such situations is
> like failing to spot a pinned piece or a passed pawn.
>

I am no fan on MC approach but basically MC can read L&D given enough
of simulations. It will read them without knowing that they need to be
analysed. Point in MC being that once you get more power you get
better L&D as well, but without extra coding.

This approach will result in non-human like game BUT likewise chess
programs did not get strong by emulating humans. They just took one
simple thing humans do and took it to extreme. Whatever approach will
do the trick in go it will be similar in this sense.

-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] The global search myth

[Petri Pitkanen]

2007/12/4, Don Dailey <[EMAIL PROTECTED]>:

> I'm not claiming this is a "good" way to proceed, I'm just trying to refute
> the idea that it would play worse with depth - this is clearly not true. Of
> course it's possible to refine this evaluation considerably - it's pretty
> lousy as I described it but I used it as an example because it's easy to
> understand and describe.
>
But let us assume that you make that simplistic eval BUT instead of
trying every move you would try only moves that are created by say
GnuGo or ManyfacesOfGo. It would play a decent game with lot less
plies. And you could safely say that considering all of the moves made
the program weaker

-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] The global search myth

[Petri Pitkanen]

2007/12/4, Álvaro Begué <[EMAIL PROTECTED]>:
>
>
>
> > Also there is not much published information evaluation functions in
> > Go. Obviously a go programming is a business and giving out such
> > information does not make sense. Best publicly available thingy is
> > GnuGo and it does not even have one.
> This was true of chess too, and there is more money to be made in computer
> chess, so my guess is that people are more secretive there.
>
But there was much more open research and with published results. And
ther are extremely good open source chess programs - you right there
were none in early eighties, but still lots off useful information was
available.

> > So selective search is part of eval.
> What? That doesn't follow at all. I'm not even sure what it means.
It means that "expert" part of selective search takes out lots of
situation that evaluation function would analyse wrongly. kind of
knowledge that chess program has in its eval go program typically has
in its move generator.

> Poor performance of current programs doesn't mean anything. People in the
> 80s could have made similar arguments saying that alpha-beta searchers with
> a simple evaluation function that considers material and positional values
But they were good already then! I played computer chess in eighties.
Yeah they were not masters yet but still could beat the average Joe
pretty easily. Road ahead was pretty clear.

And MC programs do scale really badly, better than expert programs
though. You add more simulations and they get only a little bit better
- on full sized board that is. Making computer 100 times faster would
probably not make them measurably stronger i openeing and middle-game
right now.

So I think this MC thing is a passing phase that will leave
go-programming with some new knowledge but will not be the solution.
Better evaluation functions are needed together with global search.
Then once computers get faster more candidates can be included into
search.

> only cannot possibly be the right approach, as evidenced by their funny
> moves and their poor results against humans. It turns out that an evolution
> of that approach on much faster hardware plays better than humans.
>
> Álvaro.
>
>
>
>
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>


-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] The global search myth

[Petri Pitkanen]

> There is something that the latest Monte Carlo programs have in common
> with the best chess programs - and seems to be the right way to
> structure a game tree search.Your selectivity should be
> progressive. In order to do this correctly you must re-visit nodes
> many times.  Chess programs do it iteratively and Monte Carlo UCT type
> programs do it "best first" fashion.  So the decision to prune any given
> move is a decision that is considered many times in the course of a
> search - each time taking advantage of additional information.
>

I think Monte-Carlo is more attempting solve a different issue
altogether. Sure it is a search tree buyt main problem is the
evaluation function. Currently we do not know any good way to evaluate
the situation on go board until the game is at very late stages. And I
think  - not that I could support this with any testing - that most of
the current evaluation function would not play better if they had
deeper global search and actually may play worse with wider global
search.

Relatively speaking chess eval of adding piece values together and
doing nothing else is far closer to optimal evaluation function that
what is currently available in Go.

Also there is not much published information evaluation functions in
Go. Obviously a go programming is a business and giving out such
information does not make sense. Best publicly available thingy is
GnuGo and it does not even have one.

Any simplistic Go-veal would probably result in very bad choices in
early stages of game - like playing on second row without proper
reason. So selective search is part of eval. And this shortcoming is
pretty obvious in MC programs. when they play on full sized board they
make extremely funny moves and so good result against humans only in
ultra-blitz conditions - humans scale better I guess.

Petri
-- 
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
Phone: +358 50 486 0292
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

[computer-go] Speed go next thing to explore

[Petri Pitkanen]

CrazyStone made appearance yesterday on KGS making rather impressive
record. I think it rank peaked at 1d and ended at 2k. It was playing
at speed limits of 10 minutes absolute, which seems hard for most
humans.

Also it seemed that people did not escape from the games. Rather few
unfinished games.

I think speed chess computers surpassed humans quite a while go? With
specific approach to go programming thats a frontier where progress
can be made?

Petri Pitkänen
--
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
___
computer-go mailing list
[EMAIL PROTECTED]
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Effective Go Library v0.101

[Petri Pitkanen]

2007/2/16, Nick Apperson <[EMAIL PROTECTED]>:


trouble.  Also, the alternative is usually function pointers which have
atleast 50 times the overhead of a function object.  Correct me if I'm
wrong.

- Nick


function objects really cannot be 50 times more efficient as function
pointer are rather efficient with very little overhead. Besides unless
unless function object is small enough to be inlined it will be
compiled as function pointer in many cases so there cannot be any
efficiency difference - well unless function object get inlined that
is.

Petri
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] an idea for a new measure of a computer go program's rank.

[Petri Pitkanen]

2007/1/19, Darren Cook <[EMAIL PROTECTED]>:

>> My point being that a top pro will find a high quality move in the time
>> it takes him to move the mouse from one side of the board to the other.
>
> But still it's *WAY* below his normal tournament playing strength to
> play so quickly...

Everything I know about the way top pros play says the opposite: quickly
diminishing returns from extra time. The first move they think of is
often the one they will choose even after 10 minutes of study.

Do you, or anyone, have studies that deal with this, for go? (I saw your
other post on chess, but I think this may be somewhere chess and go
differ: perhaps due the emphasis in go on good shape?)

Darren



I think this is not true for all the moves. In go there are more moves
and hence more moves with obvious best move. But Game deciding moves
are ofter ones that great deal of thinking.

But also in chess I think there is a limit on what can be gained by
adding time. After so and so many minutes/move  your decision would
not be any better. In Go this is pretty common. Like when you play
someone 9 stones weaker and they spend several minutes pondering over
move and then come up something barely better than passing. If your
eval does not know enough of situation more searching will not help.

Petri
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Gnugo vs commercial programs

[Petri Pitkanen]

2007/1/11, Don Dailey <[EMAIL PROTECTED]>:


50 X speedup sound rather impressive but it's not that much.   It's
probably
made go programs about 2 or 3 stones stronger over the few years that it
took to get hardward 50X faster about what you would expect.




But it is hardly that much. Current programs are hardly 2-3 stones
stronger ythat those in erly nineties. And if you comapare back them I
used Goliath on my 286 20 MHz computer and today I use GnuGo on my

2GHz Athlon. So in bit over decade decade computers got about 100

times faster maybe 2-3 times more effetc/cycle so almost 300 times
faster. And gain in strength is about 2-3 stones.

So 50 times faster is lot faster. It will take more than few years to
come. It may not help that much. Obviously any speed gain will help MC
type program but I doubt not too much. MC probably will not dominate
computer go in next decade. I am pretty sure we need some new ideas
still to make progress. And By Go I mean a game that is played on
19x19 board. I find playing on 9x9 boring and not really a same game.

Petri Pitkänen
--
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
Phone: +358 50 486 0292
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: Fw: [computer-go] Re: Interesting problem

[Petri Pitkanen]

opponent and eventually could have passed for free. Had game been under
Japanese rules I would have been 'forced' to think whether reply was
needed and thus think a lot longer time for replies and possibly lost on
time because reply would have been needed probably too often.

Conclusion: Under Chinese rules and limited time player can end game
easier and faster than under Japanese rules when opponent tries silly
invasions.


Not really. If you are ahead you reply every move. You got the extra
prisoner so you can afford to reply, it does not change the fact that
you won. Only if you are behind you could gain victory because
opponent makes silly move that loses points

Like in example from tournament game where a bot makes hundreds of
useless moves. Rules that encourage that simply are not good.

--
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
Phone: +358 50 486 0292
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Re: Interesting problem

[Petri Pitkanen]

2007/1/4, Don Dailey <[EMAIL PROTECTED]>:


No, this inhibits the application of skill.   A "silly" invasion that
wastes time is punished in all rules sets,  but in Chinese it may not
be silly if it doesn't waste time - Japanese rules unfairly defines
these moves as "silly."

It is silly if opponents best reply is pass




Chinese is better in this regard.   You can try these invasions and
put your opponent under pressure to refute them.


Is the refutation is pass even then?


When a Japanese player has a possible invasion that he knows is
difficult
but possible to defend,  he must decide whether to play "correctly" or
whether to gamble that his opponent won't be able to find the defense.


It it is severe enough that opponent has to reply It does not matter
in any rule set. In Japanese if silly invasions needs a real
refutation player gains point for extra prisoner and loses a point
reply inside his/her own territory. No gamble there.

BUT if it is so silly that PASS only thing that is needed, why in
earth obviously the more skilled player i.e the one who knew "that
move does not even need an answer" should not be awarded a point for
it?

Remember Chinese and Japanese rules give same outcome as long as
players made same number of moves.

--
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
Phone: +358 50 486 0292
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] Re: Interesting problem

[Petri Pitkanen]

2007/1/4, Nick Wedd <[EMAIL PROTECTED]>:

In message <[EMAIL PROTECTED]>, Tapani
Raiko <[EMAIL PROTECTED]> writes
>> I assume that "cannot be captured by the opponent" means that the opponent,
>> playing first, cannot capture it.  I accept that it is unclear whether this
>> opponent is the actual one present in the game, or a hypothetical competent
>> one.
>
>In an unresolved semeai it is not clear who is the one trying to capture
>and should thus get the first move.

It is fairly clear to me.  You ask the players for the status of each
group (alive, or dead.  Alive in seki is a special case of alive). Where
they agree, you accept what they say.  Where they differ, you have to
find out "whether it can be captured", with its would-be capturer moving
first.

Of course, if the players do the finding out themselves, there is a
danger that you end up with two adjacent dead groups.  If this happens,
I am not sure what to do next.


Nick
--
Nick Wedd[EMAIL PROTECTED]


All these are rather imaginary problems really. How many times you end
arguing about the outcome of a game at the club? Japanese rules are
de-facto rules in international go and hence computer  programs should
implement them best they can.

And they problems  doe exist as Robert has pointed out, but simple
counting procedure out weights any problems encountered so far. And
besides on normal game difference is just 1 pt.

Also It is good that unsound invasions are punished. This is supposed
to be game of skill. If someone make silly invasion that does not
require answer, the more skilled player i.e player that correctly
passes should be awarded a point for his skill.


Petri
--
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
Phone: +358 50 486 0292
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] professional game libraries for pattern harvesting

[Petri Pitkanen]

2006/12/13, Anders Kierulf <[EMAIL PROTECTED]>:

> As game records are not copyrigtable it is within your rights
> to download that file.

Game records may not be copyrightable,

No "may" word needed there. They are historical facts and hence cannot
be copyrigthed at least not in EU.


but collections of game records may
be.

Nope unless (1)they are selected somehow, like 100 best Korean games
of 2005, All Korean games I could find from 2005 does not conform to
this. And (2)in some spesific order, bunch of SGF files does not
conform to this.


http://en.wikipedia.org/wiki/Database_directive). Game records in the
collection you mention were taken from GoGoD and SmartGo without permission.

Directive is bit funny in this sense, but for this particular request:
- SmartGo is not protected as you are not member of EU nor is is your
company (this is the funny part, why in earth protect just member
countries). So large part of that collection does not violate anything
- it has more sources although GoGod is probably the largest single
source. For instance Takemiya games and Cho Chikun games can easily
obtained from net anyways.
- And the smart part. Databases can extracted and used for scientific
work. Original requester indicated some sort of research use.


GoGoD (http://www.gogod.demon.co.uk/) has over 42,400 professional games in
SGF format that you can use for data mining.


And you would also get update annually so this is of value to go players
Dunno about research. 1000 more games wont make a difference.


Anders Kierulf
www.smartgo.com


Petri Pitkänen
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] professional game libraries for pattern harvesting

[Petri Pitkanen]

Or use p2p and the pirate bay. Using serch word SGF you should find
about 40 000 game collection from moyo-go.

Or even easier The Torrent:
http://torrents.thepiratebay.org/hashtorrent/3420315.torrent/40_683_Professional_Go_Games_Collection.3420315.TPB.torrent

As game records are not copyrigtable it is within your rights to
download that file.

Cheers,
Petri


2006/12/13, David Fotland <[EMAIL PROTECTED]>:

There are 30 or 40 thousand pro games available - try Go Games on Disk.
There are 40K strong amateur games available on the Many Faces of Go CD-ROM
I think KGS amateur games are available for free.

David

> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Carter Cheng
> Sent: Tuesday, December 12, 2006 1:33 AM
> To: computer-go@computer-go.org
> Subject: [computer-go] professional game libraries for
> pattern harvesting
>
>
> I noticed a few papers now mention Bayesian learning
> techniques for mining for patterns and I am curious
> where does one find libraries for this sort of thing
> are there some commercially or free game libraries to
> which the procedures described can be applied.
>
> Regards,
>
> Carter.
> ___
> computer-go mailing list
> computer-go@computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>


___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/




--
Petri Pitkänen
e-mail: [EMAIL PROTECTED]
Phone: +358 50 486 0292
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/