论文信息 - Monte-Carlo Tree Search for General Game Playing

Monte-Carlo Tree Search for General Game Playing

We present a game engine for general game playing based on UCT, a combination of Monte-Carlo and tree search. The resulting pro ram is named ARY. Despite the modest number of random games played by A RY before choosing a move, it scored quite well in the qualifying phase of the annual general game playing tournament hosted by AAAI.

T. Cazenave | J. Méhat

[1] Jacques Pitrat,et al. Realization of a general game-playing program , 1968, IFIP Congress.

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

[3] B. Pell. A STRATEGIC METAGAME PLAYER FOR GENERAL CHESS‐LIKE GAMES , 1994, Comput. Intell..

[4] Tristan Cazenave. Système d'apprentissage par auto-observation : Application au jeu de go , 1996 .

[5] Jacques Pitrat. Games: The Next Challenge , 1998, J. Int. Comput. Games Assoc..

[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.

[9] Stephan Schiffel,et al. Fluxplayer: A Successful General Game Player , 2007, AAAI.

[10] David Silver,et al. Combining Online and Offline Learning in UCT , 2007 .

[11] T. Cazenave,et al. Extended General Gaming Model , 2007 .

[12] James E. Clune,et al. Heuristic Evaluation Functions for General Game Playing , 2007, KI - Künstliche Intelligenz.