Re: [Computer-go] List problem ...
On 2019-03-29 at 06:19, Ingo Althöfer <3-hirn-ver...@gmx.de> wrote with subject “[Computer-go] List problem ...”: > Indeed, our maioing list has a severy problem. I also > do not get mails any longer, but have to look up > in the archive always. odd, I still seem to get all list mails. But I do wonder why the list mail headers say this: > To: Brian Sheppard via Computer-go > Reply-To: Brian Sheppard via Computer-go (I changed it in this my reply) Cordially, Tom ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] List problem ...
Dear Hiroshi, thanks for your interesting recent postings on the AlphaZero paper(s). I think referees told them to back their claims by more data. So the paper has larger test runs than the arxiv preprint. ** Indeed, our maioing list has a severy problem. I also do not get mails any longer, but have to look up in the archive always. Ingo. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] AlphaZero paper difference between 2017 and 2018
Hi, Number of learned positions from a game record pos steps minibatch games AlphaGoZero 293 ( 700,000 * 2048) / 4,900,000 3 days AlphaGoZero 219 (3,100,000 * 2048) / 29,000,000256 x 40 block, 40 days AlphaZero 2017 137 ( 700,000 * 4096) / 21,000,000 AlphaZero 201820 ( 700,000 * 4096) / 140,000,000 ELF 2019 154 (1,500,000 * 2048) / 20,000,000 AlphaZero(Chess) 65 ( 700,000 * 4096) / 44,000,000 AlphaZero(Shogi) 119 ( 700,000 * 4096) / 24,000,000 All Network is 256 x 20 blocks, except AlphaGoZero 40 days. Average of game moves are Go220 Chess 80 Shogi 120 So I had thought learning all positions(from a game) once is nice. But AlphaZero2018 uses only 20 positions from a game. By the way, I did not received any mails since Ingo's mail(Mar 1 2019). Erik reported in Feb 17 2019, It looks like gmail is broken again for this list. I never got Remi's Remi also reported in Mar 24 2019. (I found this from archives.) I have just found out that the list is not sending emails to my free.fr Thanks, Hiroshi Yamashita ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] codecentric Freestyle League: Round 6
Hello, tension is grwoing high in the German Freestyle League. Next Wednesday round 6 is played on KGS in room "Deutsch Ecke". Spectators are welcome, with comments in any language. Currently Paderborn (Oktgopus) is leading with 8:0, ahead of Darmstadt and Karlsruhe (8:2 each). The pairings in round 6 are: Saargenhaft - Chris the Brain & Friends Karlsruher Allerlei - Oldenburger Ozas DeepGreen (Darmstadt) - Oktgopus (a night of truth) Paderborn, Darmstadt, and Karlsruhe each are still able to win the League out of own power. https://www.althofer.de/codecentric-freistil.html Ingo. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] [CFP] Competition and Benchmark Track at 2019 IEEE Conference on Games (former IEEE CIG)
Dear all, Apologies for cross posting. I just wanted to draw your attention to the ``Competition and Benchmark'' track at this year's IEEE Conference on Games (http://ieee-cog.org/). This track invites submissions where the main topic is a game or game-related benchmark or competition. Submission can be new competition proposals, novel approaches to existing competitions, or critical commentary on competitions. Topics include but are not limited to the following: - Evaluation of AI agents. - Machine learning related to games (e.g. for predicting player or AI behaviour). - Learning forward models. - Assessment of procedural content generators. - Analysis tools for existing competitions. - Game Competitions to more general AI. If you are working on, organizing, or planning a competition and you want to write a scientific paper about it, this could be a good venue for it. *The deadline for short, vision, demo and COMPETITION papers is the 14th of May, 2019. * Have a look, and best regards, and possibly see you in London. Christoph Salge & Jialin Liu Competition and Benchmark Track Chairs The 2019 IEEE Conference on Games ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] AlphaZero paper difference between 2017 and 2018
Hi, I found AlphaZero paper Table S3 is different 2017 and 2018. 2017 2018 Mini-batches 700k 700k Training Time 34h 13d Training Games 21 million 140 million Thinking Time 800 sims, 200ms 800 sims, 200ms Training Time is 34h ->13d 9.2 times Training Games is 21 million -> 140 million 6.6 times Chess and Shogi is same. And Figure 1 is also a bit different in Shogi and Go. Chess looks same. Why these numbers are so different? Is it typo? AlphaZero(2017/12/05) Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm https://arxiv.org/abs/1712.01815 AlphaZero(2018/12/07) A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play https://deepmind.com/documents/260/alphazero_preprint.pdf Thanks, Hiroshi Yamashita ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go