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

Ingo Althofer: : >Hi Hideki, > >first of all congrats to the nice performance of Zen over the weekend! > >> Ingo and all, >> Why you care AlphaGo and DCNN so much? > >I can speak only for myself. DCNNs may be not only

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

~~ Robert: "Hey, AI, you should provide explanations!" AI: "Why?" ~~ Cheers, Rainer Date: Mon, 1 Feb 2016 08:15:12 -0600 From: "Jim O'Flaherty" To: computer-go@computer-go.org

[Computer-go] Conference CG2016 in Leiden: NN in Games

Hello everybody, some weeks ago I had given a hint already on the conference CG2016 (CG standing for "Computer and Games"), to take place in Leiden (NL) on June 29 - July 01. https://cg2016leiden.wordpress.com/ The deadline for papers has been prolonged already to February 11. In view of the

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

Hi Hideki, you put it wonderfully into two lines: ** ** ****** *** Much more economical methods should be

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

Aja, I read the paper with great interest. [Insert appropriate praises here.] I am trying to understand the part where you use reinforcement learning to improve upon the CNN trained by imitating humans. One thing that is not explained is how to determine that a game is over, particularly when a

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

You play until neither player wishes to make a move. The players are willing to move on any point that is not self-atari, and they are willing to make self-atari plays if capture would result in a Nakade (http://senseis.xmp.net/?Nakade) This correctly plays seki. From: Computer-go

[Computer-go] DCNN can solve semeai?

Hi, I made DCNN, and tried whether DCNN can understand semeai. 1. try one playout that always select DCNN highest probablity move. 2. try 100 playouts that select moves from DCNN probability. (one playout takes 4 seconds.) Result is DCNN does not understand semeai. It can play semeai like

Re: [Computer-go] Computer-go Digest, Vol 72, Issue 41

I agree. It might be interesting to set this up a while after the Lee Sedol matches if Ke Jie still holds the #1 spot at at that time. After beating the best player of the past ten years, beating the currently best player would in a way complete AlphaGo's victory over current human Go ability.

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

> someone cracked Go right before that started. Then I'd have plenty of > time to pick a new research topic." It looks like AlphaGo has > provided. It seems [1] the smart money might be on Lee Sedol: 1. Ke Jie (world champ) – limited strength…but still amazing… Less than 5% chance against Lee

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

On Mon, Feb 1, 2016 at 10:19 AM, Darren Cook wrote: > It seems [1] the smart money might be on Lee Sedol: In the DeepMind press conferences ( https://www.youtube.com/watch?v=yR017hmUSC4 - https://www.youtube.com/watch?v=_r3yF4lV0wk ) Demis Hassabis stated, that he was quietly

Re: [Computer-go] Zen19X achieved stable KGS 7d

On Mon, Feb 1, 2016 at 1:44 PM, Hideki Kato wrote: > I was, btw, really surprised when Zen beat fj with two stones > handi. > http://files.gokgs.com/games/2016/1/31/Zen19X-fj.sgf > > Hideki On the DGoB forums fj stated, possibly in jest, that this was an even game, as he

Re: [Computer-go] Zen19X achieved stable KGS 7d

On Sun, Jan 31, 2016 at 10:16:25AM +0900, Hideki Kato wrote: > Petr Baudis: <20160130150502.gf12...@machine.or.cz>: > > Hi, > > > > it seems that Zen19X grabbed at KGS 7d and looks like it's gonna hold! > > > > > > http://www.gokgs.com/gameArchives.jsp?user=zen19x=2016=1=y > > > >It's

Re: [Computer-go] AlphaGo and the Standard Mistake in Research and Journalism

> > > I am pretty sure that such an implicit expression exists: it is << the >> number of etc etc >> > > We do not speak of just the definition of what kind of number to find, but > of the construction of finding the number (or already of a compression of > its explicit digits). It's hard to

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

The next type of event could be a new 'Pair Go' Where a human and a program make up a pair, like Mark Zuckerberg and his facebook program against a Google VP and alphaGo. :-) Thomas On Mon, 1 Feb 2016, John Tromp wrote: For those of you who missed it, chess grandmaster Hikaru Nakamura, rated

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

Robert, I'm not seeing the ROI in attempting to map human idiosyncratic linguistic systems to/into a Go engine. Which language would be the one to use; English, Chinese, Japanese, etc? As abstraction goes deeper, the nuance of each human language diverges from the others (due to the way the human

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

Hi! On Mon, Feb 01, 2016 at 01:38:28PM +, Aja Huang wrote: > On Mon, Feb 1, 2016 at 11:38 AM, Petr Baudis wrote: > > > > That's right, but unless I've overlooked something, I didn't see Fan Hui > > create any complicated fight, there wasn't any semeai or complex > > life

Re: [Computer-go] AlphaGo and the Standard Mistake in Research and Journalism

> > > How do you know that an implicit expression (of length smaller than 10^80) > of the number does not exist? :) > I am pretty sure that such an implicit expression exists: it is << the number of etc etc >> (formalized for your favorite set of rules :-) ). --

Re: [Computer-go] The Game AI Forum is back

Thank you very much. Personally I find it much easier to keep up with and follow topics in this kind of format. Perhaps we can encourage people who post on the mailing list to post on your Forum instead/too? -Richard P.S. Happy New Year! On 01/01/2016 12:56 AM, Rémi Coulom wrote: Hi, I

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

On Mon, Feb 01, 2016 at 12:24:21PM +0100, Olivier Teytaud wrote: > If AlphaGo had lost at least one game, I'd understand how people can have > an upper bound on its level, but with 5-0 (except for Blitz) it's hard to > have an upper bound on his level. After all, AlphaGo might just have played >

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

Olivier Teytaud:

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

Hi! On Mon, Feb 01, 2016 at 09:19:56AM +, Darren Cook wrote: > > someone cracked Go right before that started. Then I'd have plenty of > > time to pick a new research topic." It looks like AlphaGo has > > provided. > > It seems [1] the smart money might be on Lee Sedol: > > 1. Ke Jie

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

If AlphaGo had lost at least one game, I'd understand how people can have an upper bound on its level, but with 5-0 (except for Blitz) it's hard to have an upper bound on his level. After all, AlphaGo might just have played well enough for crushing Fan Hui, and a weak move while the position is

Re: [Computer-go] Zen19X achieved stable KGS 7d

Congrats to Zen's achievements! :) Aja On Mon, Feb 1, 2016 at 11:44 AM, Petr Baudis wrote: > On Sun, Jan 31, 2016 at 10:16:25AM +0900, Hideki Kato wrote: > > Petr Baudis: <20160130150502.gf12...@machine.or.cz>: > > > Hi, > > > > > > it seems that Zen19X grabbed at KGS 7d and

Re: [Computer-go] Zen19X achieved stable KGS 7d

Aja Huang:

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

Ok, it's not blitz according to http://senseis.xmp.net/?BlitzGames (limit at 10s/move for Blitz). But really shorter time settings. I've seen (as you all) many posts guessing that AlphaGo will lose, but I find that hard to know. If Fan Hui had won one game, I would say that AlphaGo is not ready

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

For those of you who missed it, chess grandmaster Hikaru Nakamura, rated 2787, recently played a match against the world's top chess program Komodo, rated 3368. Each of the 4 games used a different kind of handicap: Pawn and Move Odds Pawn Odds Exchange Odds 4-Move Odds As you can see, handicaps

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

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

If anything, the other great DCNN applications predate the application of these methods to Go. Deep neural nets (convnets and other types) have been successfully applied in computer vision, robotics, speech recognition, machine translation, natural language processing, and hosts of other areas.

Re: [Computer-go] DCNN can solve semeai?

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 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

[Computer-go] Last CFP: GCIRE2016 | GREEN COMPUTING, INTELLIGENT AND RENEWABLE ENERGIES | Philippines

THE SECOND INTERNATIONAL CONFERENCE ON GREEN COMPUTING, INTELLIGENT AND RENEWABLE ENERGIES (GCIRE2016) Where: University of Perpetual Help System DALTA, Las Piñas, Manila, Philippines When: February 24-26, 2016 Website: http://bit.do/gcire2016 Publication: The Society of Digital Information and

Re: [Computer-go] The Game AI Forum is back

Tysvm for the clarification. I appreciate and agree with your reasons. :) On Mon, Feb 1, 2016 at 8:20 AM, Rémi Coulom wrote: > I did not create a go sub-forum in order to not compete with this mailing > list. As long as there is not a strong agreement of all the members of

Re: [Computer-go] The Game AI Forum is back

I did not create a go sub-forum in order to not compete with this mailing list. As long as there is not a strong agreement of all the members of the list to move there, I feel that splitting into two online discussion places would be detrimental. I won't censor topics about the game of Go on

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

On 01.02.2016 15:15, Jim O'Flaherty wrote: I'm not seeing the ROI in attempting to map human idiosyncratic linguistic systems to/into a Go engine. Which language would be the one to use; English, Chinese, Japanese, etc? As abstraction goes deeper, the nuance of each human language diverges from

Re: [Computer-go] Zen19X achieved stable KGS 7d

Thanks, it's very reasonable :) Hideki Michael Markefka: : >On Mon, Feb 1, 2016 at 1:44 PM, Hideki Kato wrote: >> I was, btw, really surprised when Zen beat fj with two stones >> handi. >>

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

Hi Hideki, first of all congrats to the nice performance of Zen over the weekend! > Ingo and all, > Why you care AlphaGo and DCNN so much? I can speak only for myself. DCNNs may be not only applied to achieve better playing strength. One may use them to create playing styles, or bots for go

Re: [Computer-go] Match Conditions?

Hi Aja, congratulations again to the fantastic achievement of your team! One bunch of management questions:   * How many games will be played in March between Alpha-Go and Lee Sedol? * Will it be just "X games" or some "best of X" format? * What will be the thinking times? * Will there be rest

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

On 01.02.2016 14:38, Aja Huang wrote: AlphaGo may do much better in tactical situations than Crazy Stone and Zen. Judging very quickly from the Fan Hui games, AlphaGo's group-local "reading" is very deep and accurate but I'd need to read for myself equally deeply and carefully before I would

Re: [Computer-go] The Game AI Forum is back

Richard, I'm probably missing the obvious, I went to the forum, but was unable to find a forum specifically for Go. I found Abolone, Hex and several others. Thank you, Jim On Fri, Jan 1, 2016 at 9:08 AM, Richard Lorentz wrote: > Thank you very much. Personally I