[Computer-go] Replicating AlphaGo results

[Petr Baudis]

  Hi!

  Since I didn't say that yet, congratulations to DeepMind!

  (I guess I'm a bit disappointed that no really new ML models had to be
invented for this though, I was wondering e.g. about capsule networks or
training simple iterative evaluation subroutines (for semeai etc.) by
NTM-based approaches.  Just like everyone else, color me very awed by
such an astonishing result with just what was presented.)

On Wed, Jan 27, 2016 at 11:15:59PM -0800, David Fotland wrote:
> Google’s breakthrough is just as impactful as the invention of MCTS.  
> Congratulations to the team.  It’s a huge leap for computer go, but more 
> importantly it shows that DNN can be applied to many other difficult problems.
> 
> I just added an answer.  I don’t think anyone will try to exactly replicate 
> it, but a year from now there should be several strong programs using very 
> similar techniques, with similar strength.
> 
> An interesting question is, who has integrated or is integrating a DNN into 
> their go program?  I’m working on it.  I know there are several others.
> 
> David
> 
> From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
> Jason Li
> Sent: Wednesday, January 27, 2016 3:14 PM
> To: computer-go@computer-go.org
> Subject: Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks 
> and Tree Search
> 
> Congratulations to Aja!
> 
> A question to the community. Is anyone going to replicate the experimental 
> results?
> 
> https://www.quora.com/Is-anyone-replicating-the-experimental-results-of-the-human-level-Go-player-published-by-Google-Deepmind-in-Nature-in-January-2016?

  A perfect question, I think - what can we do to replicate this,
without Google's computational power?

  I probably couldn't have resisted giving it a try myself (especially
given that a lot of what I do nowadays are deep NNs, though on NLP),
but thankfully I have two deadlines coming... ;-)

  I'd propose these as the major technical points to consider when
bringing a Go program (or a new one) to an Alpha-Go analog:

  * Asynchronous integration of DNN evaluation with fast MCTS.  I'm
curious about this, as I thought this would be a much bigger problem
that it apparently is, based on old results with batch parallelization.
I guess virtual loss makes a lot of difference?  Is 1 lost playout enough?
I wonder if Detlef has already solved this sufficiently well in oakfoam?

What's the typical lag of getting the GPU evaluation (in, I guess,
#playouts) in oakfoam and is the throughput sufficient to score all
expanded leaf nodes (what's the #visits?)?  Sorry if this has been
answered before.

  * Are RL Policy Networks essential?  AIUI by quick reading, they are
actually used only for RL of the value networks, and based on Fig. 4
the value network didn't use policy network for training on but still
got quite stronger than zen/crazystone?  Aside of extra work, this'd
save us 50 GPU-days.

(My intuition is that RL policy networks are the part that allows
embedding knowledge about common tsumego/semeai situations in the
value networks, because they probably have enough capacity to learn
them.  Does that make sense?)

  * Seems like the push for SL Policy Network prediction accuracy from
50% to 60% is really important for real-world strength (Fig. 2).
I think right now the top open source solution has prediction
accuracy 50%?  IDK if there's any other factor (features, dataset
size, training procedure) involved in this than "Updates were
applied asynchronously on 50 GPUs using DistBelief 60; gradients older
than 100 steps were discarded. Training took around 3 weeks for 340
million training steps."

  * Value Networks require (i) 30 million self-play games (!); (ii) 50
GPU-weeks to train the weights.  This seems rather troublesome, even
1/10 of that is a bit problematic for individual programmers.  It'd
be interesting to see how much of that are diminishing returns and
if a much smaller network on smaller data (+ some compromises like
sampling the same game a few times, or adding the 8 million tygem
corpus to the mix) could do something interesting too.

  In summary, seems to me that the big part of why this approach was so
successful are the huge computational resources applied to this, which
is of course an obstacle (except the big IT companies).

  I think the next main avenue of research is exploring solutions that
are much less resource-hungry.  The main problem here is hungry at
training time, not play time.  Well, the strength of this NN running on
a normal single-GPU machine is another big question mark, of course.

Petr Baudis
___
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

[Michael Markefka]

On Thu, Jan 28, 2016 at 3:14 PM, Stefan Kaitschick
 wrote:

> That "value network" is just amazing to me.
> It does what computer go failed at for over 20 years, and what MCTS was
> designed to sidestep.

Thought it worth a mention: Detlef posted about trying to train a CNN
on win rate as well in February. So it seems he was onto something
there.
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Replicating AlphaGo results

[Petr Baudis]

On Thu, Jan 28, 2016 at 10:29:29AM -0600, Jim O'Flaherty wrote:
> I think the first goal was and is to find a pathway that clearly works to
> reach into the upper echelons of human strength, even if the first version
> used a huge amount of resources. Once found, then the approach can be
> explored for efficiencies from both directions, top down (take this away
> and see what we lose, if anything) and bottom up (efficiently reoriginate a
> reflection of a larger pattern in a much more constrained environment).
> >From what I can see in the chess community, this is essentially what
> happened following Deep Blue's win against Kasperov. And now their are
> solutions on single desktops that can best what Deep Blue did with far more
> computational resources.

  Certainly!

  Also, reflecting on what I just wrote,

> On Thu, Jan 28, 2016 at 10:07 AM, Petr Baudis  wrote:
> >
> >   (I guess I'm a bit disappointed that no really new ML models had to be
> > invented for this though, I was wondering e.g. about capsule networks or
> > training simple iterative evaluation subroutines (for semeai etc.) by
> > NTM-based approaches.  Just like everyone else, color me very awed by
> > such an astonishing result with just what was presented.)
> >
> >   In summary, seems to me that the big part of why this approach was so
> > successful are the huge computational resources applied to this, which
> > is of course an obstacle (except the big IT companies).

  this is not meant at all as a criticism of AlphaGo, purely just
a discussion point!  Even if you have a lot of hardware, it's *hard* to
make it add value, as anyone who tried to run MCTS on a cluster could
testify - it's not just a matter of throwing it at the problem, and the
challenges aren't just engineering-related either.

  So maybe I'd actually say that this was even understated in the paper
- that AlphaGo uses an approach which scales so well with available
computational power (at training time) compared to previous approaches.

-- 
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

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

[Stefan Kaitschick]

I always thought the same. But I don't think they tackled the decomposition
problem directly.
Achieving good(non-terminal) board evaluations must have reduced the
problem.
If you don't do full playouts, you get much less thrashing between
independent problems.
It also implies a useful static L evaluation.
That "value network" is just amazing to me.
It does what computer go failed at for over 20 years, and what MCTS was
designed to sidestep.
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Replicating AlphaGo results

[Jim O'Flaherty]

I think the first goal was and is to find a pathway that clearly works to
reach into the upper echelons of human strength, even if the first version
used a huge amount of resources. Once found, then the approach can be
explored for efficiencies from both directions, top down (take this away
and see what we lose, if anything) and bottom up (efficiently reoriginate a
reflection of a larger pattern in a much more constrained environment).
>From what I can see in the chess community, this is essentially what
happened following Deep Blue's win against Kasperov. And now their are
solutions on single desktops that can best what Deep Blue did with far more
computational resources.


On Thu, Jan 28, 2016 at 10:07 AM, Petr Baudis  wrote:

>   Hi!
>
>   Since I didn't say that yet, congratulations to DeepMind!
>
>   (I guess I'm a bit disappointed that no really new ML models had to be
> invented for this though, I was wondering e.g. about capsule networks or
> training simple iterative evaluation subroutines (for semeai etc.) by
> NTM-based approaches.  Just like everyone else, color me very awed by
> such an astonishing result with just what was presented.)
>
> On Wed, Jan 27, 2016 at 11:15:59PM -0800, David Fotland wrote:
> > Google’s breakthrough is just as impactful as the invention of MCTS.
> Congratulations to the team.  It’s a huge leap for computer go, but more
> importantly it shows that DNN can be applied to many other difficult
> problems.
> >
> > I just added an answer.  I don’t think anyone will try to exactly
> replicate it, but a year from now there should be several strong programs
> using very similar techniques, with similar strength.
> >
> > An interesting question is, who has integrated or is integrating a DNN
> into their go program?  I’m working on it.  I know there are several others.
> >
> > David
> >
> > From: Computer-go [mailto:computer-go-boun...@computer-go.org] On
> Behalf Of Jason Li
> > Sent: Wednesday, January 27, 2016 3:14 PM
> > To: computer-go@computer-go.org
> > Subject: Re: [Computer-go] Mastering the Game of Go with Deep Neural
> Networks and Tree Search
> >
> > Congratulations to Aja!
> >
> > A question to the community. Is anyone going to replicate the
> experimental results?
> >
> >
> https://www.quora.com/Is-anyone-replicating-the-experimental-results-of-the-human-level-Go-player-published-by-Google-Deepmind-in-Nature-in-January-2016
> ?
>
>   A perfect question, I think - what can we do to replicate this,
> without Google's computational power?
>
>   I probably couldn't have resisted giving it a try myself (especially
> given that a lot of what I do nowadays are deep NNs, though on NLP),
> but thankfully I have two deadlines coming... ;-)
>
>   I'd propose these as the major technical points to consider when
> bringing a Go program (or a new one) to an Alpha-Go analog:
>
>   * Asynchronous integration of DNN evaluation with fast MCTS.  I'm
> curious about this, as I thought this would be a much bigger problem
> that it apparently is, based on old results with batch parallelization.
> I guess virtual loss makes a lot of difference?  Is 1 lost playout
> enough?
> I wonder if Detlef has already solved this sufficiently well in
> oakfoam?
>
> What's the typical lag of getting the GPU evaluation (in, I guess,
> #playouts) in oakfoam and is the throughput sufficient to score all
> expanded leaf nodes (what's the #visits?)?  Sorry if this has been
> answered before.
>
>   * Are RL Policy Networks essential?  AIUI by quick reading, they are
> actually used only for RL of the value networks, and based on Fig. 4
> the value network didn't use policy network for training on but still
> got quite stronger than zen/crazystone?  Aside of extra work, this'd
> save us 50 GPU-days.
>
> (My intuition is that RL policy networks are the part that allows
> embedding knowledge about common tsumego/semeai situations in the
> value networks, because they probably have enough capacity to learn
> them.  Does that make sense?)
>
>   * Seems like the push for SL Policy Network prediction accuracy from
> 50% to 60% is really important for real-world strength (Fig. 2).
> I think right now the top open source solution has prediction
> accuracy 50%?  IDK if there's any other factor (features, dataset
> size, training procedure) involved in this than "Updates were
> applied asynchronously on 50 GPUs using DistBelief 60; gradients older
> than 100 steps were discarded. Training took around 3 weeks for 340
> million training steps."
>
>   * Value Networks require (i) 30 million self-play games (!); (ii) 50
> GPU-weeks to train the weights.  This seems rather troublesome, even
> 1/10 of that is a bit problematic for individual programmers.  It'd
> be interesting to see how much of that are diminishing returns and
> if a much smaller network on smaller data (+ some compromises like
> 

Re: [Computer-go] Replicating AlphaGo results

[Darren Cook]

>   I'd propose these as the major technical points to consider when
> bringing a Go program (or a new one) to an Alpha-Go analog:
> ...
>   * Are RL Policy Networks essential?  ...

Figure 4b was really interesting (see also Extended Tables 7 and 9): any
2 of their 3 components, on a single machine, are stronger than Crazy
Stone and Zen. And the value of the missing component:

   Policy Network: +813 elo
 Rollouts: +713 elo
Value Network: +474 elo

Darren

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

Re: [Computer-go] Game Over

[Brian Sheppard]

I would just mention that Maven/Scrabble truncated rollouts are not comparable 
to Go/MCTS truncated rollouts. An evaluation function in Scrabble is readily at 
hand, because scoring points is hugely correlated with winning. There is no 
evaluation function for Go that is readily at hand.

There have been some efforts at whole-board evaluation in Go. Maybe NeuroGo was 
the earliest really cool demonstration. But I never saw anything that gave me 
confidence that the approach could work when embedded in an MCTS framework. I 
am blown away.

-Original Message-
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
"Ingo Althöfer"
Sent: Thursday, January 28, 2016 1:00 AM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] Game Over

Hello Anders,

thanks for the summary on the smartgo site.

> ... the truncated rollouts mentioned in the paper are still unclear to me.

The greatest expert on these rollouts might be Richard Lorentz.
He applied them successfully to his bots in the games Amazons (not to be mixed 
up
with the online bookshop), Havannah and Breakthrough. Richard found that in many
applications a truncation level of 4 moves seem to work quite well.
There is a paper by him on this topic in the proceedings of the conference
Advances in Computer Games 2015 (in Leiden , NL), published by Springer
Lecture Notes in Computer Science (LNCS).

A very early application of truncated rollouts was applied by Brian
Sheppard in his bot for Scrabble (MAVEN).

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

[Michael Alford]

On 1/27/16 12:08 PM, Aja Huang wrote:


2016-01-27 18:46 GMT+00:00 Aja Huang >:

Hi all,

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. We hope you enjoy our
paper, published in Nature today. The paper and all the games can be
found here:

http://www.deepmind.com/alpha-go.html


The paper is freely available to download at the bottom of the page.
https://storage.googleapis.com/deepmind-data/assets/papers/deepmind-mastering-go.pdf

Aja

AlphaGo will be competing in a match against Lee Sedol in Seoul,
this March, to see whether we finally have a Go program that is
stronger than any human!

Aja

PS I am very busy preparing AlphaGo for the match, so apologies in
advance if I cannot respond to all questions about AlphaGo.



Congratulations on your achievement. While scanning the web articles 
yesterday, I came across this one:


http://www.bloomberg.com/news/articles/2016-01-27/google-computers-defeat-human-players-at-2-500-year-old-board-game

It states that the winner of the March match gets $1mil. This is the 
only reference to any prize I have found. Is it correct?


Thank you,
Michael



___
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



--

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

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

[Ingo Althöfer]

Hi Simon,

do your remember my silly remarks in an email discussion almost a year ago?

You had written:
>> So, yes, with all the exciting work in DCNN, it is very tempting 
>> to also do DCNN. But I am not sure if we should do so.

And my silly reply had been:
> I think that DCNN is somehow in a dreamdancing appartment.
> My opinion: We might mention it in our proposal, but not as a central topic.
 

In my mathematical life I have been wrong with my intuition only a few times.
This DCNN topic was the worst case so far...

Greetings from the bottom,
Ingo.

 

Gesendet: Donnerstag, 28. Januar 2016 um 16:41 Uhr
Von: "Lucas, Simon M" 
An: "computer-go@computer-go.org" 
Betreff: Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks 
and Tree Search

Indeed – Congratulations to Google DeepMind!
 
It’s truly an immense achievement.  I’m struggling
to think of other examples of reasonably mature
and strongly contested AI challenges where a new
system has made such a huge improvement over
existing systems – and I’m still struggling …
 
Simon Lucas
___
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

[valkyria]

Congratulations!

What I find most impressive is the engineering effort, combining so many 
different parts, which even standalone would be a strong program.


I think the design philosophy of using 3 different sources of "go 
playing" strength is great in it self (and if you read the paper there 
are a lot of old school computer go programming expetise used as well). 
I think we oft get stuck trying to perfect one module when perhaps what 
we need is a new module that improves search effectively on a different  
scale. I have not time and resources to do neural networks learning, but 
for my new program I would like to experimentwith using patterns on many 
levels, and this is inspiring.


Magnus Persson

On 2016-01-27 19:46, Aja Huang wrote:

Hi all,

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. We hope you enjoy our
paper, published in Nature today. The paper and all the games can be
found here:

http://www.deepmind.com/alpha-go.html [1]

AlphaGo will be competing in a match against Lee Sedol in Seoul, this
March, to see whether we finally have a Go program that is stronger
than any human!

Aja

PS I am very busy preparing AlphaGo for the match, so apologies in
advance if I cannot respond to all questions about AlphaGo.

Links:
--
[1] http://www.deepmind.com/alpha-go.html

___
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] Game Over

[Robert Jasiek]

On 28.01.2016 04:57, Anders Kierulf wrote:

Please let me know if I misinterpreted anything.


You write "Position evaluation has not worked well for Go in the past" 
but I think you should write "...Computer Go..." because applicable, 
reasonably accurate theory for human players' positional evaluation 
exists, see e.g. my two books Positional Judgement.


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

Re: [Computer-go] Game Over

[Michael Markefka]

I find it interesting that right until he ends his review, Antti only
praises White's moves, which are the human ones. When he stops, he
even considers a win by White as basically inevitable.

Now Fan Hui either blundered badly afterwards, or more promising, it
could be hard for humans to evaluate AlphaGo's play at this point
because they undervalue some it its choices. Which of course would be
similar to how some moves by the first world-beating chess AIs have
been treated by human experts.

AlphaGo might be even more of a wild card than it seems.


Also, on another note, that Google set up those Sedol games makes me
assume that they are convinced of actually succeeding. The Fan Hui
matches have been months ago, and AlphaGo will have spent that time
learning, and when the matches come around they will probably throw A
LOT of processing power at Sedol. I don't think they would try for so
much public reach to then fail and be associated with failure and
hybris.

On Thu, Jan 28, 2016 at 12:12 PM, J. van der Steen
 wrote:
>
> Hi Xavier,
>
> Really nice comments by Antti Törmänen, to the point and very clear
> explanation. Thanks for the pointer.
>
> best regards,
> Jan van der Steen
>
> On 28-01-16 11:45, Xavier Combelle wrote:
>>
>> here a comment by Antti Törmänen
>>
>> http://gooften.net/2016/01/28/the-future-is-here-a-professional-level-go-ai/
>>
>> 2016-01-28 11:19 GMT+01:00 Darren Cook > >:
>>
>> > If you want to view them in the browser, I've also put them on my
>> blog:
>>
>> >http://www.furidamu.org/blog/2016/01/26/mastering-the-game-of-go-with-deep-neural-networks-and-tree-search/
>> > (scroll down)
>>
>> Thanks. Has anyone (strong) made commented versions yet? I played
>> through the first game, but it just looks like a game between two
>> players much stronger than me :-)
>>
>> (Ingo, are you analyzing them with e.g. CrazyStone? Is there a
>> particular point where it adjusts who it thinks is winning?)
>>
>> 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] Game Over

[Michael Markefka]

That would make my writing nonsense of course. :)

Thanks for the pointer.

On Thu, Jan 28, 2016 at 12:26 PM, Xavier Combelle
 wrote:
>
>
> 2016-01-28 12:23 GMT+01:00 Michael Markefka :
>>
>> I find it interesting that right until he ends his review, Antti only
>> praises White's moves, which are the human ones. When he stops, he
>> even considers a win by White as basically inevitable.
>>
> White moves are the AI ones, check the players
>
>
> ___
> 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] Game Over

[J. van der Steen]

Hi Xavier,

Really nice comments by Antti Törmänen, to the point and very clear 
explanation. Thanks for the pointer.


best regards,
Jan van der Steen

On 28-01-16 11:45, Xavier Combelle wrote:

here a comment by Antti Törmänen
http://gooften.net/2016/01/28/the-future-is-here-a-professional-level-go-ai/

2016-01-28 11:19 GMT+01:00 Darren Cook >:

> If you want to view them in the browser, I've also put them on my blog:

>http://www.furidamu.org/blog/2016/01/26/mastering-the-game-of-go-with-deep-neural-networks-and-tree-search/
> (scroll down)

Thanks. Has anyone (strong) made commented versions yet? I played
through the first game, but it just looks like a game between two
players much stronger than me :-)

(Ingo, are you analyzing them with e.g. CrazyStone? Is there a
particular point where it adjusts who it thinks is winning?)

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

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

[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

Re: [Computer-go] Game Over

[Xavier Combelle]

here a comment by Antti Törmänen
http://gooften.net/2016/01/28/the-future-is-here-a-professional-level-go-ai/

2016-01-28 11:19 GMT+01:00 Darren Cook :

> > If you want to view them in the browser, I've also put them on my blog:
> >
> http://www.furidamu.org/blog/2016/01/26/mastering-the-game-of-go-with-deep-neural-networks-and-tree-search/
> > (scroll down)
>
> Thanks. Has anyone (strong) made commented versions yet? I played
> through the first game, but it just looks like a game between two
> players much stronger than me :-)
>
> (Ingo, are you analyzing them with e.g. CrazyStone? Is there a
> particular point where it adjusts who it thinks is winning?)
>
> 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

Re: [Computer-go] Game Over

[Darren Cook]

> If you want to view them in the browser, I've also put them on my blog:
> http://www.furidamu.org/blog/2016/01/26/mastering-the-game-of-go-with-deep-neural-networks-and-tree-search/
> (scroll down)

Thanks. Has anyone (strong) made commented versions yet? I played
through the first game, but it just looks like a game between two
players much stronger than me :-)

(Ingo, are you analyzing them with e.g. CrazyStone? Is there a
particular point where it adjusts who it thinks is winning?)

Darren

___
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] Game Over

[Darren Cook]

> here a comment by Antti Törmänen
> http://gooften.net/2016/01/28/the-future-is-here-a-professional-level-go-ai/

Thanks, exactly what I was looking for. He points out black 85 and 95
might be mistakes, but didn't point out any dubious white (computer)
moves. He picks out a couple of white moves as particularly good, e.g.
108, which is also an empty triangle: obviously AlphaGo isn't being held
back by any "good shape" heuristics ;-)

I hope he comments the other four games!

Darren


-- 
Darren Cook, Software Researcher/Developer
My new book: Data Push Apps with HTML5 SSE
Published by O'Reilly: (ask me for a discount code!)
  http://shop.oreilly.com/product/0636920030928.do
Also on Amazon and at all good booksellers!
___
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

[Lucas, Simon M]

Indeed – Congratulations to Google DeepMind!

It’s truly an immense achievement.  I’m struggling
to think of other examples of reasonably mature
and strongly contested AI challenges where a new
system has made such a huge improvement over
existing systems – and I’m still struggling …

Simon Lucas



From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Olivier Teytaud
Sent: 27 January 2016 20:27
To: computer-go 
Subject: Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks 
and Tree Search

Congratulations people at DeepMind :-)

I like the fact that alphaGo uses many forms of learning (as humans do!):
- imitation learning (on expert games, learning an actor policy);
- learning by playing (self play, policy gradient), incidentally generating 
games;
- use of those games for teaching a second deep network (supervised learning);
- real time learning with Monte Carlo simulations (including Rave ?).
==> just beautiful :-)




2016-01-27 21:18 GMT+01:00 Yamato 
>:
Congratulations Aja.

Do you have a plan to run AlphaGo on KGS?

It must be a 9d!

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



--
=
Olivier Teytaud, olivier.teyt...@inria.fr, 
TAO, LRI, UMR 8623(CNRS - Univ. Paris-Sud),
bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France 
http://www.slideshare.net/teytaud
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go