A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information

Mathematical Programming, Series B

Volumn 95, Issue 3, 2003, Pages 513-532

  Raghavan, T E S ^a   Syed, Zamir ^b  

^a UNIVERSITY OF ILLINOIS AT CHICAGO   (United States)

^b Hull Group LLC   (United States)

Author keywords

MDP; Perfect information; Policy iteration; Stochastic games

Indexed keywords

MDP; PERFECT INFORMATION; POLICY ITERATION; STOCHASTIC GAMES;

GAME THEORY; INFORMATION THEORY; PROBLEM SOLVING; PUBLIC POLICY; THEOREM PROVING;

ALGORITHMS;

EID: 33746343278     PISSN: 00255610     EISSN: None     Source Type: Journal    
DOI: 10.1007/s10107-002-0312-3     Document Type: Article

References (24)

1. Blackwell, D. [1962]: Discrete Dynamic Programming. Annals of Mathematical Statistics 33, 719-726.
2. Condon, A. [1992]: The Complexity of Stochastic Games. Information and Computing 96. 203-224.
3. Derman, C. [1970]: Finite State Markovian Decision Processes. Academic Press, New York.
4. Everett, H. [1957]: Recursive Games, In: Dresher, M., A.W. Tucker & P. Wolfe (eds.), pp 47-78. Contribution to the theory of games, Vol. III, Ann. of Math. Stud. 39, Princeton Univ. Press, Princeton.
5. Filar, J.A. and O.J. Vrieze [1996]: Competitive Markov Decision Processes, Springer Verlag, Berlin.
6. Gillette, D. [1957]: Stochastic games with zero stop probabilities, In: Dresher, M., A.W. Tucker & P. Wolfe (eds.), pp 179-188. Contribution to the theory of games, Vol. III, Ann. of Math. Stud. 39, Princeton Univ. Press, Princeton.
7. Gurwich, V.A. Karzanov, A.V. and L.G. Khachiyan [1988]: Cyclic games and an algorithm to find minimax cycle means in directed graphs, USSR Computational Mathematics and Mathe,matical Physics, 28, 85-91.
8. Hoffman, A.J. and Karp, R.M. [1966]: On Non-Terminating Stochastic Games. Management Science, 12, 359-370.
9. Hordijk, A. and Kallenberg, L.C.M. [1979]: Linear Programming and Markovian Decision Chains. Management Science 25, 352-362.
10. Howard, R.A. [1960]: Dynamic Programming and Markov Processes, Wiley, New York.
11. Kallenberg, L.C.M. [1983]: Linear Programming and Finite Markovian Control Problems. Mathematical Centre Tract 148, Centre for Mathematics and Computer Science, Amsterdam.
12. Kachian L.G. [1979]: A polynomial algorithm in linear programming. Soviet Math. Doklady, 20, 191-194.
13. Liggett, T.M. and S. A. Lippman [1969]: Stochastic Games with Perfect Information and Time Average Payoff. SIAM Review 11, 604-607.
14. Ludwig, W. [1995]: A subexponential Randomized Algorithm for the Simple Stochastic Game Problem. Information and Computation 117, 151-155.
15. Melekopoglou, M. and A. Condon [1994]: On the Complexity of the Policy Improvement Algorithm for Markov Decision Processes. ORSA Journal on Computing 6, 188-192.
16. Miller, B and A. Veinott Jr. [1969]: Discrete Dynamic Programming with a Small Interest Rate Ann. Math. Statistics 40, 366-370.
17. Parthasarathy, T. and T.E.S. Raghavan [1981]: An order field property for stochastic games when one player controls transition probabilities, J. Optimization Theory and Appl. 33:375-392.
18. Pollatschek and Avi-Itzhak [1969]: Algorithms for Stochastic Games with Geometrical Interpretation Management Science 15, 399-415.
19. Raghavan T.E.S. and J.A. Filar [1991]: Algorithms for Stochastic Games - A Survey Methods and Models of Operations Research ZOR 35:437-472.
20. Shapley, L.S. [1953]: Stochastic Games Proceedings of the National Academy of Sciences U.S.A. 39, 1095-1100.
21. Van der Waal, J. [1977]: Discounted Markov Games: Successive Approximations and Stopping Times International J. Game Theory 6, 11-22.
22. Veinott, A. Jr. [1966]: On Finding Optimal Policies in Discrete Dynamic Programming with no Discounting, 37, 1284-1294.
23. O.J. Vrieze [1983]: Stochastic Games with Finite State and Action Spaces, (Ph.D Thesis), Free University, Math. Centrum, Amsterdam.
24. Zwick, U and M.S. Paterson [1996]: The complexity of mean payoff games on graphs. Theoretical Computer Science, 158, 343-359.