Near-optimal polynomial time algorithm for learning in certain classes of stochastic games

Artificial Intelligence

Volumn 121, Issue 1, 2000, Pages 31-47

  Brafman, Ronen I ^a   Tennenholtz, Moshe ^b  

^a BEN GURION UNIVERSITY OF THE NEGEV   (Israel)

^b TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION THEORY; GAME THEORY; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES; POLYNOMIALS;

MULTI-AGENT SYSTEMS; POLYNOMIAL TIME LEARNING SYSTEMS; STOCHASTIC GAMES;

ARTIFICIAL INTELLIGENCE;

EID: 0034247018     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0004-3702(00)00039-4     Document Type: Article

References (10)

1. Alon N., Spencer J.H., Erdos P. The Probabilistic Method. 1992;Wiley, New York.
2. Chernoff H. A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann. Math. Statist. Vol. 23:1952;493-509.
3. Horijk A., Kallenberg L.C.M. Linear programming and Markov games. Moeschlin O. Game Theory and Mathematical Economics. 1981;307-319 North-Holland, Amsterdam.
4. Hu J., Wellman M.P. Multiagent reinforcement learning: Theoretical framework and an algorithm. Proc. 15th International Conference on Machine Learning (ICML-98), Madison, WI. 1998.
5. Kearns M., Singh S. Near-optimal reinforcement learning in polynomial time. Proc. 15th International Conference on Machine Learning (ICML-98), Madison, WI. 1998.
6. Littman M.L. Markov games as a framework for multi-agent reinforcement learning. Proc. 11th International Conference on Machine Learning, New Brunswick, NJ. 1994;157-163.
7. Monderer D., Tennenholtz M. Dynamic non-Bayesian decision-making. J. Artificial Intelligence Res. Vol. 7:1997;231-248.
8. Parthasarathy T., Raghavan T.E.S. An order field property for stochastic games when one player controls transition probabilities. J. Optim. Theory Appl. Vol. 33:1981;375-392.
9. Shapley L.S. Stochastic games. Proc. Nat. Acad. Sci. USA. Vol. 39:1953;1095-1100.
10. Vrieze O.J. Linear programming and undiscounted stochastic game in which one player controls transitions. OR Spektrum. Vol. 3:1981;29-35.