[Computer-go] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
yss at bd.mbn.or.jp
Wed Dec 6 01:24:28 PST 2017
DeepMind makes strongest Chess and Shogi programs with AlphaGo Zero method.
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
AlphaZero(Chess) outperformed Stockfish after 4 hours,
AlphaZero(Shogi) outperformed elmo after 2 hours.
Search is MCTS.
AlphaZero(Chess) searches 80,000 positions/sec.
Stockfish searches 70,000,000 positions/sec.
AlphaZero(Shogi) searches 40,000 positions/sec.
elmo searches 35,000,000 positions/sec.
More information about the Computer-go