论文信息 - Nonlinear programming and stationary strategies in stochastic games

Nonlinear programming and stationary strategies in stochastic games

We show that an undiscounted stochastic game possesses optimal stationary strategies if and only if a global minimum with objective value zero can be found to an appropriate nonlinear program with linear constraints. This nonlinear program arises as a method for solving a certain bilinear system, satisfaction of which is also equivalent to finding a stationary optimal solution for the game. The objective function of the program is a nonnegatively valued quadric polynomial.

Jerzy A. Filar | Todd A. Schultz

[1] A single loop stochastic game which one player can terminate , 1981 .

[2] Elon Kohlberg,et al. On Stochastic Games with Stationary Optimal Strategies , 1978, Math. Oper. Res..

[3] O. J. Vrieze,et al. Stochastic Games with Finite State and Action Spaces. , 1988 .

[4] A. Hordijk,et al. Linear Programming and Markov Decision Chains , 1979 .

[5] L. C. M. Kallenberg,et al. Linear programming and finite Markovian control problems , 1984 .

[6] O. J. Vrieze,et al. On stochastic games with additive reward and transition structure , 1985 .

[7] D. Blackwell,et al. THE BIG MATCH , 1968, Classics in Game Theory.

[8] L. Shapley,et al. Stochastic Games* , 1953, Proceedings of the National Academy of Sciences.

[9] M. J. Sobel. Noncooperative Stochastic Games , 1971 .

[10] Stef Tijs,et al. Stochastic games with state independent transitions and separable rewards , 1984 .

[11] R. Karp,et al. On Nonterminating Stochastic Games , 1966 .

[12] J. Filar. Ordered field property for stochastic games when the player who controls transitions changes from state to state , 1981 .

[13] T. Parthasarathy,et al. An orderfield property for stochastic games when one player controls transition probabilities , 1981 .