[Computer-go] Patterns and bad shape

Hi, I'm sure the topic must have come up before but i can't seem to find it right now, i'd appreciate if someone can point me in the right direction. I'm looking into MM, LFR and similar cpu-based pattern approaches for generating priors, and was wondering about basic bad shape: Let's say we

Re: [Computer-go] Patterns and bad shape

It seems chasing down good moves for bad shapes would be an explosion of "exception cases", like combinatorially huge. So, while you would be saving some branching in the search space, you would be ballooning up the number of patterns for which to scan by orders of magnitude. Wouldn't it be prefer

Re: [Computer-go] Patterns and bad shape

I highly doubt that learning refutations to pertinent bad shape patterns is much more exponential or combinatorially huge than learning good shape already is, if you could somehow be appropriately selective about it. There are enough commonalities that it should "compress" very well into what the n

Re: [Computer-go] Patterns and bad shape

Hmmm, screenshot doesn't seem to be getting through to the list, so here's a textual graphic instead. A B C D E F G H J K L M N O P Q R S T +---+ 19 | . . . . . . . . . . . . . . . . . . . | 18 | . . . . . . . . . . . . . . . . . . . | 17 | . .

[Computer-go] Welcome to Download the "computer go dataset" (160K 9D vs 9D SGFs)

2015.11.02 - 2016.12.31 TYGEM "9D vs 9D" dataset (1,516,031 games). 2003.09.25 - 2011.12.28 TOM "9D vs 9D" dataset (50,956 games). https://github.com/yenw/computer-go-dataset ___ Computer-go mailing list Computer-go@computer-go

Re: [Computer-go] Patterns and bad shape

On Mon, Apr 17, 2017 at 3:04 PM, David Wu wrote: > To some degree this maybe means Leela is insufficiently explorative in > cases like this, but still, why does the policy net not put H5 more than > 1.03%. After all, it's vastly more likely than 1% that that a good player > will see the ladder wo

Re: [Computer-go] Patterns and bad shape

Hmm. Do you know that Leela does something special here? When I look at Leela's analysis output it seems to the search seems not to consider the ladder escape because the policy net assigns a low probability to it (and such a high probability to move in the upper right). Which is the same as in oth

Re: [Computer-go] Welcome to Download the "computer go dataset" (160K 9D vs 9D SGFs)

On Mon, Apr 17, 2017 at 4:19 PM, Yu Yuan wrote: > 2015.11.02 - 2016.12.31 > TYGEM "9D vs 9D" dataset (1,516,031 games). > > 2003.09.25 - 2011.12.28 > TOM "9D vs 9D" dataset (50,956 games). > Hi Yu Yuan, I was wondering did you check with TYGEM and TOM about the copyright of these SGFs? Aja >

Re: [Computer-go] Patterns and bad shape

David Wu wrote: > Black (X) to move. The screenshot showed that Leela's policy net put about > 96% probability on a and only 1.03% on b. And that even after nearly 1 > million simulations had basically not searched b at all. Leela does read out ladders to the end, it doesn't rely on policy netwo

Re: [Computer-go] Welcome to Download the "computer go dataset" (160K9D vs 9D SGFs)

Hi Yu Yuan, Thanks! I wrote a converter. http://www.yss-aya.com/20170418tygem_convert.tar.gz I could not convert some of Tygem 2011 and 2014, because of id mismatch. Thanks, Hiroshi Yamashita - Original Message - From: "Yu Yuan" To: Sent: Tuesday, April 18, 2017 12:19 AM Subject: [

Re: [Computer-go] Welcome to Download the "computer go dataset" (160K 9D vs 9D SGFs)

How did you get these files? I'm sure that at least Tygem guys think the game records are their own property. On 2017/04/18 0:19, Yu Yuan wrote: > 2015.11.02 - 2016.12.31 > TYGEM "9D vs 9D" dataset (1,516,031 games). > > 2003.09.25 - 2011.12.28 > TOM "9D vs 9D" dataset (50,956 games). > > http