Re: [Computer-go] New paper by DeepMind
More games in general. looks like more chess games than previously available(wasn't it previously just 100, now it is 210) and it looks like they addressed the flack they got from the chess community by moving the hash size from 1G to 32G for stockfish. On Thu, Dec 6, 2018 at 4:12 PM Rémi Coulom wrote: > > Interesting, thanks. I had not found pseudocode.py. > > It is in that file: > http://science.sciencemag.org/highwire/filestream/719481/field_highwire_adjunct_files/1/aar6404_DataS1.zip > > The link is at the bottom of that page: > http://science.sciencemag.org/content/362/6419/1140/tab-figures-data > > Rémi > > - Mail original - > De: "Dan Schmidt" > À: computer-go@computer-go.org > Envoyé: Jeudi 6 Décembre 2018 23:39:57 > Objet: Re: [Computer-go] New paper by DeepMind > > > > > I believe that the dependence of C(s) (formerly c_puct) on N(s) is new. > > > The file pseudocode.py in the supplementary download sets c_base to 19652 and > c_init to 1.25. > > > Dan > > > > On Thu, Dec 6, 2018 at 5:27 PM Rémi Coulom < remi.cou...@free.fr > wrote: > > > Hi, > > The new alphazero paper of DeepMind about chess and shogi has been published > in Science: > > https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/ > > pdf: > https://deepmind.com/documents/260/alphazero_preprint.pdf > > I tried to play "spot the difference" with their previous draft, and did not > notice any very important difference. They include shogi games, which might > be appreciated by the shogi players. It seems they still don't tell the value > of their exploration coefficient, unless I missed anything. > > Also, the AlphaZero algorithm is patented: > https://patentscope2.wipo.int/search/en/detail.jsf?docId=WO2018215665 > > Rémi > ___ > 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] it's alphago
Oh sorry I mispoke, corporate players losing interest is a bad thing in my mind but also more or less inevitable(to some degree anyway). I was simply saying that as delighted as I am that google and other players are putting so much money and research into go I suspect eventually the resources will be re-allocated to other things, and having a large community network would help push things forward even after/if resources dwindle. Just as you point out deepmind is not selling their bot and I think aren't motivated as much by the game of go so much as the AI breakthroughs it represents. Even if many others players stay fairly active I think the resources currently invested in go are larger than the market for go bots. For example in the chess world there are some valuable chess engines but the engines are now limited mostly to companies that directly sell the engines or community/non-profit efforts. I suspect at some point go will be the same. On Fri, Jan 6, 2017 at 10:49 AM, Marc Landgraf <mahrgel...@gmail.com> wrote: > And why would it be desirable that 'the big corporate players lose > interest to devote computer power'? > And who are those big corporate players? Deepmind? Who are not even > selling their bot? Or are you talking about CS/Zen who are having indeed > financial interests here? > What would be the benefit of any of those parties in losing interest? > > Am 06.01.2017 17:22 schrieb "daniel rich" <qianyil...@gmail.com>: > >> A closer example than the mersenne prime search is fishtest from the >> chess engine world. My understanding is that it is a key part of why >> stockfish is such a strong chessengine. >> >> https://github.com/glinscott/fishtest >> >> A large group of volunteers that essentially donate compute power to test >> changes and improve the bot. That would be a fairly cool way compute time >> to be made available to the community. The plus is that eventually big >> corporate players may lose interest to devote the same level of spending >> and compute that we have seen so far. >> >> >> >> On Fri, Jan 6, 2017 at 8:01 AM, Lukas van de Wiel < >> lukas.drinkt.t...@gmail.com> wrote: >> >>> A project similar to the Great Mersenne Prime search might be a >>> possibility to distribute the work of training the network among many >>> enthousiasts, and to keep improving it by self play. >>> >>> On 1/6/17, Andy <andy.olsen...@gmail.com> wrote: >>> > What is Ray? Strongest open source bot? Anyone have a link to it? >>> > >>> > On Fri, Jan 6, 2017 at 3:39 AM, Hiroshi Yamashita <y...@bd.mbn.or.jp> >>> wrote: >>> > >>> >> If value net is the most important part for over pro level, the >>> problem >>> >> is >>> >> making strong selfplay games. >>> >> >>> >> 1. make 30 million selfplay games. >>> >> 2. make value net. >>> >> 3. use this value net for selfplay program. >>> >> 4. go to (1) >>> >> >>> >> I don't know when the progress will stop by this loop. >>> >> But if once strong enough selfplay games are published, everyone can >>> make >>> >> pro level program. >>> >> 30 million is big number. It needs many computers. >>> >> Computer Go community may be able to share this work. >>> >> I can offer Aya, it is not open-source though. Maybe Ray(strongest >>> open >>> >> source so far) is better choice. >>> >> >>> >> Thanks, >>> >> Hiroshi Yamashita >>> >> >>> >> - Original Message - From: <fotl...@smart-games.com> >>> >> To: <computer-go@computer-go.org> >>> >> Sent: Friday, January 06, 2017 4:50 PM >>> >> Subject: Re: [Computer-go] it's alphago >>> >> >>> >> >>> >> Competitive with Alpha-go, one developer, not possible. I do think it >>> is >>> >> possible to make a pro level program with one person or a small team. >>> >> Look >>> >> at Deep Zen and Aya for example. I expect I’ll get there (pro level) >>> with >>> >> Many Faces as well. >>> >> >>> >> David >>> >> >>> >> ___ >>> >> 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] it's alphago
A closer example than the mersenne prime search is fishtest from the chess engine world. My understanding is that it is a key part of why stockfish is such a strong chessengine. https://github.com/glinscott/fishtest A large group of volunteers that essentially donate compute power to test changes and improve the bot. That would be a fairly cool way compute time to be made available to the community. The plus is that eventually big corporate players may lose interest to devote the same level of spending and compute that we have seen so far. On Fri, Jan 6, 2017 at 8:01 AM, Lukas van de Wiel < lukas.drinkt.t...@gmail.com> wrote: > A project similar to the Great Mersenne Prime search might be a > possibility to distribute the work of training the network among many > enthousiasts, and to keep improving it by self play. > > On 1/6/17, Andywrote: > > What is Ray? Strongest open source bot? Anyone have a link to it? > > > > On Fri, Jan 6, 2017 at 3:39 AM, Hiroshi Yamashita > wrote: > > > >> If value net is the most important part for over pro level, the problem > >> is > >> making strong selfplay games. > >> > >> 1. make 30 million selfplay games. > >> 2. make value net. > >> 3. use this value net for selfplay program. > >> 4. go to (1) > >> > >> I don't know when the progress will stop by this loop. > >> But if once strong enough selfplay games are published, everyone can > make > >> pro level program. > >> 30 million is big number. It needs many computers. > >> Computer Go community may be able to share this work. > >> I can offer Aya, it is not open-source though. Maybe Ray(strongest open > >> source so far) is better choice. > >> > >> Thanks, > >> Hiroshi Yamashita > >> > >> - Original Message - From: > >> To: > >> Sent: Friday, January 06, 2017 4:50 PM > >> Subject: Re: [Computer-go] it's alphago > >> > >> > >> Competitive with Alpha-go, one developer, not possible. I do think it is > >> possible to make a pro level program with one person or a small team. > >> Look > >> at Deep Zen and Aya for example. I expect I’ll get there (pro level) > with > >> Many Faces as well. > >> > >> David > >> > >> ___ > >> 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] Crazystone on Steam
I may try it using crossover. Also to clarify despite steam being on linux most steam games are not usable on linux. If you notice the sys requirements still call out windows for this game. On Sun, May 29, 2016 at 12:48 AM, Phil <p...@credo.org.uk> wrote: > > Steam is on Linux: > http://store.steampowered.com/about/ > I haven't tried it yet. > > > > On 27/05/16 21:10, daniel rich wrote: > > Anyone have any idea how well crazy stone does in Wine? Or if Mac/Linux > support will happen? > > > > On Fri, May 27, 2016 at 1:23 PM, Marc Landgraf <mahrgel...@gmail.com> > wrote: > >> Oh, this is great. >> But one question: Will there be any updates/upgrades/patches for client >> and/or engine? >> Having it on Steam would finally give a convenient way to do so. This >> would be a reason for me to buy it, hoping for it to change for the better. >> Or will it just be a one release policy? Can't see myself spending 74euro >> then, considering the mixed reviews in various places. >> Am 27.05.2016 21:09 schrieb "Jim O'Flaherty" <jim.oflaherty...@gmail.com >> >: >> >>> Tysvm! The video on Stream is a very nice touch. And the first review >>> rocks! >>> >>> On Fri, May 27, 2016 at 1:36 PM, Andreas Persson < <andr...@apgames.se> >>> andr...@apgames.se> wrote: >>> >>>> Congrats on the Steam release of Crazystone Rémi! Hope it will sell >>>> well. For people that haven't seen it here is a link >>>> <http://store.steampowered.com/app/479330/> >>>> http://store.steampowered.com/app/479330/. Bit to pricey for me but >>>> will pick it up at some point, enjoy the ios app a lot. >>>> >>>> /Andreas >>>> >>>> ___ >>>> 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 > 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] Crazystone on Steam
Anyone have any idea how well crazy stone does in Wine? Or if Mac/Linux support will happen? On Fri, May 27, 2016 at 1:23 PM, Marc Landgrafwrote: > Oh, this is great. > But one question: Will there be any updates/upgrades/patches for client > and/or engine? > Having it on Steam would finally give a convenient way to do so. This > would be a reason for me to buy it, hoping for it to change for the better. > Or will it just be a one release policy? Can't see myself spending 74euro > then, considering the mixed reviews in various places. > Am 27.05.2016 21:09 schrieb "Jim O'Flaherty" : > >> Tysvm! The video on Stream is a very nice touch. And the first review >> rocks! >> >> On Fri, May 27, 2016 at 1:36 PM, Andreas Persson >> wrote: >> >>> Congrats on the Steam release of Crazystone Rémi! Hope it will sell >>> well. For people that haven't seen it here is a link >>> http://store.steampowered.com/app/479330/. Bit to pricey for me but >>> will pick it up at some point, enjoy the ios app a lot. >>> >>> /Andreas >>> >>> ___ >>> 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] new bot friendly go server.
Nice, Thanks Henry! I am in the process of bringing up my first bot(as are a bunch of people) so I will probably try and connect in the next couple of days. --Danny On Mon, May 23, 2016 at 8:46 AM, Petr Baudiswrote: > Hi! > > On Sun, May 22, 2016 at 08:56:09AM +, Henry Hemming wrote: > > Hello, I would like to invite all you go bot developers to my new go > server. > > > > http://goratingserver.appspot.com > > I tried a game last evening too. I didn't mind not being able to > choose my nickname too much (I just clicked until I got a rodent nick ;), > and I liked the mechanics and minimalism in general. > > However, at the end of the game both me and my opponent became a bit > confused as we didn't realize we have to capture dead stones; I'd > strongly suggest adding ability to mark dead stones before releasing it > to wider audience; playing it out is really tedious and my opponent > didn't realize they had to do it at all (the message is not so well > visible, they might not know English or even know how to read). > > I'm not sure if I'll return; if I wanted to play in the browser, I'd > pick OGS and it doesn't seem clear what the advantages of your server > are, possibly besides your unique rating algorithm (which I'd also love > to hear more about). > > -- > 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] Darkforest (Facebook) AI estimating
Nice find! On Mon, Mar 14, 2016 at 4:05 PM, Paweł Morawiecki < pawel.morawie...@gmail.com> wrote: > Hi, > > It looks like this http://zhuanlan.zhihu.com/yuandong/20639694 > is an analysis of Facebook AI of Game 1 and 2. > > I just looked at it very briefly but, interestingly, in Game 2 Darkforest > agrees with pro commentators who said that Lee Sedol #70 (S15) was slow and > it would be better to chase black's group in the centre. Indeed Darkforest > suggested F10. > > Details:http://www.yuandong-tian.com/win_rate2.txt > > Regards, > Pawel > > ___ > 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