Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis (Submitted on 5 Dec 2017) The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case. 0051名無し名人2017/12/07(木) 20:37:15.26ID:lWmx5nfG 一つ疑問なのが将棋よりもチェスのほうが時間かかってるってとこだな将棋の方が時間かかりそうなもんだが まぁエルモが大したこと無かったってことかも知らんが 0052名無し名人2017/12/07(木) 20:37:51.77ID:SMPAIy/f>>48 お前痛いな… 0053名無し名人2017/12/07(木) 20:39:46.77ID:5Dw6I7us>>47 そのdeep learning て、ぽな山本がなんか頑張って実用化しようとしたんだけど、うまくいかずにエルモび負けたんじゃん。でもGoogleの子会社は、deep leaningでエルモに圧勝したんじゃろ?
Elo ratings were computed from evaluation games between different players when given one second per move 1手1分だから強いとかも嘘だね
棋譜生成は Unless otherwise specified, the training and search algorithm and parameters are identical to AlphaGo Zero AlphaGo Zeroと全く同じ学習法使っていて measure false positives, we disable resignation in 10% of self-play games and play until termination. だから10%の対局は確実に終局までやってる 0092名無し名人2017/12/07(木) 21:37:42.43ID:SMPAIy/f>>89 いや、それは確かに一応少しは今回の件に関係あるとも言える >>36のお馬鹿な国民性の話とは全然違うぞ 0093名無し名人2017/12/07(木) 21:47:49.00ID:fkWw/Xte コンピューター将棋という分野が終了 AIの砂場になりましたw 0094名無し名人2017/12/07(木) 21:50:16.60ID:5Dw6I7us>>92
36 >人的資源と金の投資が桁違いということかね 0095名無し名人2017/12/07(木) 21:54:21.01ID:DWFIOBo9>>36 著者名全部調べてないけど米国人いるの? D. Silver と D. Hassabis は少なくとも英国人だろ なおハサビスは 1/4 中国系(祖父が華人系シンガポール人) 0096名無し名人2017/12/07(木) 21:54:23.67ID:S1OD81BE 専門家の方にはシンギュラリティについて詳しく説明できる方がいるはずですけど、シンギュラリティは産業革命の類の存在では無いのですか?詳しく教えてくれますよね?