论文信息 - Playing the Right Atari

Playing the Right Atari

We experimented a simple yet powerful optimization for Monte-Carlo Go tree search. It consists in dealing appropriately with strings that have two liberties. The heuristic is contained in one page of code and the Go program that uses it improves from 50 % of won games against Gnugo 3.6 to 76 % of won games.

Tristan Cazenave | T. Cazenave

[1] Bernd Brügmann Max-Planck. Monte Carlo Go , 1993 .

[2] Bruno Bouzy,et al. Associating Shallow and Selective Global Tree Search with Monte Carlo for 9*9 Go , 2004, Computers and Games.

[3] Bruno Bouzy,et al. Associating domain-dependent knowledge and Monte Carlo approaches within a Go program , 2005, Inf. Sci..

[4] Tristan Cazenave,et al. Combining Tactical Search and Monte-Carlo in the Game of Go , 2005, CIG.

[5] Sylvain Gelly,et al. Exploration exploitation in Go: UCT for Monte-Carlo Go , 2006, NIPS 2006.

[6] Olivier Teytaud,et al. Modification of UCT with Patterns in Monte-Carlo Go , 2006 .

[7] Rémi Coulom,et al. Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search , 2006, Computers and Games.

[8] Csaba Szepesvári,et al. Bandit Based Monte-Carlo Planning , 2006, ECML.