Algorithms for Stochastic Games with Geometrical Interpretation
暂无分享,去创建一个
The paper presents a new approach, based on analysis and geometrical interpretation, to the solution of Markov stochastic games. The proposed algorithm, using iterations in policy space, turns out to be a Newton-Raphson type procedure. Several numerical examples are given, covering the terminating and non-terminating cases respectively and illustrating the advantages of the proposed algorithm compared with other known algorithms. Special attention is given to Howard's sequential decision problem with discrete and continuous policy spaces.
[1] L. Shapley,et al. Stochastic Games* , 1953, Proceedings of the National Academy of Sciences.
[2] Ronald A. Howard,et al. Dynamic Programming and Markov Processes , 1960 .
[3] Samuel Karlin,et al. Mathematical Methods and Theory in Games, Programming, and Economics , 1961 .
[4] John G. Kemeny,et al. Finite Markov Chains. , 1960 .
[5] R. Karp,et al. On Nonterminating Stochastic Games , 1966 .