Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

[Shawn Ligocki]

Thanks for sharing the games, Rémi!

On Thu, May 7, 2020 at 6:27 AM Rémi Coulom  wrote:

> In this game, Crazy Stone won using a typical Monte Carlo trick:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
> On move 27, it sacrificed a stone. According to Crazy Stone, the game
> would have been a draw had Aya just re-captured it. But Aya took the bait
> and captured the other stone. Crazy Stone's evaluation became instantly
> winning after this, the sacrificed stone serving as a threat for the
> winning ko fight, 18 moves later.
>

Wow, I did not imagine how that move would be useful later! But the very
end is confusing to my human brain, couldn't White move 56 retake the ko
and win it? It seems like Black only has one real ko threat left (J4
maybe). But White also has one huge threat left (D3), so it seems like
White should win this ko and then be about 4 ahead with komi. Am I
missing something?

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

Re: [Computer-go] 0.5-point wins in Go vs Extremely slow LeelaChessZero wins

[Shawn Ligocki]

I wonder if this behavior could be avoided by giving a small incentive to
win by the most points (or most material in chess) similar to to the
technique mentioned by David Wu in KataGo a few days ago. The problem right
now is that the AI has literally no reason to think that winning with more
points is better than by 0.5 points, whereas human players prefer to win by
more points slightly. David, have you noticed if KataGo avoids these sorts
of losing point moves at the end of the game?

(I feel the same reasoning applies to automatic cars, they could be (and
probably are) trained to prefer smoother ride in addition to avoiding
accidents.)

On Tue, Mar 5, 2019 at 5:11 PM "Ingo Althöfer" <3-hirn-ver...@gmx.de> wrote:

> Hi,
>
> recently, Leela-Chess-Zero has become very strong, playing
> on the same level with Stockfish-10. Many of the test players
> are puzzled, however, by the "phenomenon" that Lc0 tends to
> need many many moves to transform an overwhelming advantage
> into a mate.
>
> Just today a new German tester reported a case and described
> it by the sentence "da wird der Hund in der Pfanne verrückt"
> ("now the dog is going crazy in the pan", to translate it word
> by word). He had seen an endgame: Stockfish with naked king,
> and LeelaZero with king, queen and two rooks. Leela first
> sacrificed the queen, then one of the rooks, and only then
> started to go for a "normal" mate with the last remaining rook
> (+ king). The guy (Florian Wieting) asked for an explanation.
>
> http://forum.computerschach.de/cgi-bin/mwf/topic_show.pl?tid=10262
>
> I think there is a very straightforward one: What Leela-Chess-Zero
> with its MCTS-based searc) performs is comparable to the
> path all MCTS Go bots took for many years when playing winning
> positions against human opponents: the advantage was reduced
> step by step, and in the end the bot gained a win by 0.5 points.
> Later, in the tournament table, that was not a problem, because
> a win is a win :-)
>
> Similarly in chess: overwhelming advantage is reduced by lazy play
> to some small margin advantage (against a straightforward alpha-beta
> opponent), and then the MCTS chess bot (= Leela Zero in this case)
> starts playing concentratedly.
>
> Another guy asked how DeepMind had worked around this problem
> with their AlphaZero. I am rather convinced: They also had this
> problem. Likely, they kept the most serious examples undisclosed,
> and furthermore set the margins for resignation rather narrow (for
> instance something like evaluation +-6 by Stockfish for three move
> pairs) to avoid nearly endless endgames.
>
> Ingo.
>
> PS: thinking of a future with automatic cars in public traffic. The
> 0.5-point wins or the related behaviour in MCTS-based chess would mean
> that an automatic car would brake only in the very last moment
> knowing that it will be sufficient to stop 20 centimeters next to the
> back-bumpers of the car ahead. Of course, a human passenger would
> not like to experience such situations too 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] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

[Shawn Ligocki]

On Thu, Oct 26, 2017 at 2:02 PM, Gian-Carlo Pascutto  wrote:

> On 26-10-17 15:55, Roel van Engelen wrote:
> > @Gian-Carlo Pascutto
> >
> > Since training uses a ridiculous amount of computing power i wonder
> > if it would be useful to make certain changes for future research,
> > like training the value head with multiple komi values
> > 
>
> Given that the game data will be available, it will be trivial for
> anyone to train a different network architecture on the result and see
> if they get better results, or a program that handles multiple komi
> values, etc.
>
> The problem is getting the *data*, not the training.
>

But the data should be different for different komi values, right?
Iteratively producing self-play games and training with the goal of
optimizing for komi 7 should converge to a different optimal player than
optimizing for komi 5. But maybe having high quality data for komi 7 will
still save a lot of the work for training a komi 5 (or komi agnostic)
network?
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

[Shawn Ligocki]

My guess is that they want to distribute playing millions of self-play
games. Then the learning would be comparatively much faster. Is that right?

On Wed, Oct 25, 2017 at 11:57 AM, Xavier Combelle  wrote:

> Is there some way to distribute learning of a neural network ?
>
> Le 25/10/2017 à 05:43, Andy a écrit :
>
> Gian-Carlo, I didn't realize at first that you were planning to create a
> crowd-sourced project. I hope this project can get off the ground and
> running!
>
> I'll look into installing this but I always find it hard to get all the
> tool chain stuff going.
>
>
>
> 2017-10-24 15:02 GMT-05:00 Gian-Carlo Pascutto :
>
>> On 23-10-17 10:39, Darren Cook wrote:
>> >> The source of AlphaGo Zero is really of zero interest (pun intended).
>> >
>> > The source code is the first-hand account of how it works, whereas an
>> > academic paper is a second-hand account. So, definitely not zero use.
>>
>> This should be fairly accurate:
>>
>> https://github.com/gcp/leela-zero
>>
>> --
>> GCP
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>
>
>
>
> ___
> Computer-go mailing 
> listComputer-go@computer-go.orghttp://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] Zero is weaker than Master!?

[Shawn Ligocki]

Also (if I'm understanding the paper correctly) 20 blocks ~= 40 layers
because each "block" has two convolution layers:

Each residual block applies the following modules sequentially to its input:
> (1) A convolution of 256 filters of kernel size 3×3 with stride 1
> (2) Batch normalization
> (3) A rectifier nonlinearity
> (4) A convolution of 256 filters of kernel size 3×3 with stride 1
> (5) Batch normalization
> (6) A skip connection that adds the input to the block
> (7) A rectifier nonlinearity


On Tue, Oct 24, 2017 at 5:10 PM, Xavier Combelle 
wrote:

> How is it a fair comparison if there is only 3 days of training for Zero ?
> Master had longer training no ? Moreover, Zero has bootstrap problem
> because at the opposite of Master it don't learn from expert games
> which means that it is likely to be weaker with little training.
>
>
> Le 24/10/2017 à 20:20, Hideki Kato a écrit :
> > David Silver told Master used 40 layers network in May.
> > According to new paper, Master used the same architecture
> > as Zero.  So, Master used 20 blocks ResNet.
> >
> > The first instance of Zero, 20 blocks ResNet version, is
> > weaker than Master (after 3 days training).  So, with the
> > same layers (a fair comparison) Zero is weaker than
> > Master.
> >
> > Hideki
>
>
> ___
> 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] Ke Jie vs. AlphaGo match

[Shawn Ligocki]

The same schedule is on a new Google site (appears to be China timezone).
It also says that there will be Livestream:

http://events.google.com/alphago2017/index.html

On May 19, 2017 07:26, "Hiroshi Yamashita"  wrote:

> Is it japanese tome zone?
>>
>
>
> I think it is Japanese time. So UTC is
>
> Ke Jie vs. AlphaGo  (3 hours + 1 minute x5)
> Game1May 23   02:30-09:30
> Game2May 25   02:30-09:30
> Game3May 27   02:30-09:30
>
> Pair Go  May 26   00:30-03:30
> Team Go  May 26   04:30-10:30
>
> Panda net site says game record live is available.
> Viewer soft is free, but I'm not sure whether guest account is ok.
>
> Ke Jie vs. AlphaGo
> Moves
> http://ugi.pandanet.co.jp/?key=alphago-2017-1
> Moves with comment by Rin Kono 9 pro
> http://ugi.pandanet.co.jp/?key=alphago-2017-1c
>
> Pair Go
> Moves
> http://ugi.pandanet.co.jp/?key=alphago-2017-4
> Moves with comment by Daisuke Murakawa 8 pro
> http://ugi.pandanet.co.jp/?key=alphago-2017-4c
>
> Team Go
> Moves
> http://ugi.pandanet.co.jp/?key=alphago-2017-5
> Moves with comment by Daisuke Murakawa 8 pro
> http://ugi.pandanet.co.jp/?key=alphago-2017-5c
>
> Viewer for Windows
> http://www.pandanet.co.jp/setup/
> Viewer for iPhone
> https://itunes.apple.com/jp/app/pandanet-go/id406456426
> Viewer for Android
> https://play.google.com/store/apps/details?id=be.gentgo.tets
> uki=search_result#?t=W251bGwsMSwxLDEsImJlLmdlbnRnby50ZXRzdWtpIl0.
>
> Thanks,
> Hiroshi Yamashita
>
> - Original Message - From: "Xavier Combelle" <
> xavier.combe...@gmail.com>
> To: 
> Sent: Friday, May 19, 2017 3:52 PM
> Subject: Re: [Computer-go] Ke Jie vs. AlphaGo match
>
>
> Is it japanese tome zone?
>
> ___
> 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