论文信息 - Fictitious play in ‘one-against-all’ multi-player games

Fictitious play in ‘one-against-all’ multi-player games

Summary. A compound game is an (n + 1) player game based on n two-person subgames. In each of these subgames player 0 plays against one of the other players. Player 0 is regulated, so that he must choose the same strategy in all n subgames. We show that every fictitious play process approaches the set of equilibria in compound games for which all subgames are either zero-sum games, potential games, or $2\times 2$ games.

Aner Sela

[1] Aner Sela,et al. Fictitious Play in 2 × 3 Games , 2000, Games Econ. Behav..

[2] Vijay Krishna,et al. Learning in Games: Fictitious Play Dynamics , 1997 .

[3] C. Harris. On the Rate of Convergence of Continuous-Time Fictitious Play , 1998 .

[4] J. Robinson. AN ITERATIVE METHOD OF SOLVING A GAME , 1951, Classics in Game Theory.

[5] L. Shapley,et al. Fictitious Play Property for Games with Identical Interests , 1996 .

[6] Ben Polak,et al. Fictitious play in 2×2 games: A geometric proof of convergence , 1994 .

[7] L. Shapley. SOME TOPICS IN TWO-PERSON GAMES , 1963 .

[8] Vijay Krishna,et al. On the Convergence of Fictitious Play , 1998, Math. Oper. Res..

[9] Paul R. Milgrom,et al. Adaptive and sophisticated learning in normal form games , 1991 .

[10] D. Monderer,et al. Fictitious play and- no-cycling conditions , 1997 .