Stationary Strategies in Zero-Sum Stochastic Games
暂无分享,去创建一个
We deal with zero-sum stochastic games. We demonstrate the importance of stationary strategies by showing that stationary strategies are better (in terms of the rewards they guarantee for a player, against any strategy of his opponent) than (1) pure strategies (even history-dependent ones), (2) strategies which may use only a finite number of different mixed actions in any state, and (3) strategies with finite recall. Examples are given to clarify the issues.
[1] János Flesch,et al. Markov Strategies are Better than stationary Strategies , 1999, IGTR.
[2] S. Lippman,et al. Stochastic Games with Perfect Information and Time Average Payoff , 1969 .
[3] D. Blackwell,et al. THE BIG MATCH , 1968, Classics in Game Theory.
[4] Dean Gillette,et al. 9. STOCHASTIC GAMES WITH ZERO STOP PROBABILITIES , 1958 .
[5] L. Shapley,et al. Stochastic Games* , 1953, Proceedings of the National Academy of Sciences.