Generalised weakened fictitious play

Games and Economic Behavior

Volumn 56, Issue 2, 2006, Pages 285-298

  Leslie, David S ^a   Collins, E J ^b  

^a UNIVERSITY OF OXFORD   (United Kingdom)

^b UNIVERSITY OF BRISTOL   (United Kingdom)

Author keywords

Actor critic process; Best response differential inclusion; Fictitious play; Stochastic approximation

Indexed keywords

EID: 33744514808     PISSN: 08998256     EISSN: 10902473     Source Type: Journal    
DOI: 10.1016/j.geb.2005.08.005     Document Type: Article

References (33)

1. Beggs A.W. On the convergence of reinforcement learning. J. Econ. Theory 122 (2005) 1-36
2. Benaïm M., and Hirsch M.W. Mixed equilibria and dynamical systems arising from fictitious play in perturbed games. Games Econ. Behav. 29 (1999) 36-72
3. Benaïm M., Hofbauer J., and Sorin S. Stochastic approximation and differential inclusions. SIAM J. Control Optim. 44 (2005) 328-348
4. Berger, U., 2004. Two more classes of games with the fictitious play property. Mimeo. Vienna University of Economics
5. Berger U. Fictitious play in 2 × n games. J. Econ. Theory 120 (2005) 139-154
6. Börgers T., and Sarin R. Learning through reinforcement and replicator dynamics. J. Econ. Theory 77 (1997) 1-14
7. Brown G.W. Iterative solution of games by fictitious play. In: Koopmans T.C. (Ed). Activity Analysis of Production and Allocation (1951), Wiley, New York 374-376
8. Conley C.C. Isolated invariant sets and the Morse index. CBMS Regional Conference Series in Mathematics (1978), American Mathematical Society, Providence
9. Cowan, S., 1992. Dynamical systems arising from game theory. Ph.D. thesis. University of California, Berkeley
10. Foster D.P., and Young H.P. Learning, hypothesis testing, and Nash equilibrium. Games Econ. Behav. 45 (2003) 73-96
11. Foster D.P., and Young H.P. Regret testing: A simple payoff-based procedure for learning Nash equilibrium. Available at. http://www.econ.jhu.edu/People/Young/
12. Fudenberg D., and Kreps D.M. Learning mixed equilibria. Games Econ. Behav. 5 (1993) 320-367
13. Fudenberg D., and Levine D.K. The Theory of Learning in Games (1998), MIT Press, Cambridge, MA
14. Gilboa I., and Matsui A. Social stability and equilibrium. Econometrica 59 (1991) 859-867
15. Hart S., and Mas-Colell A. A reinforcement procedure leading to correlated equilibrium. In: Debreu G., Neuefeind W., and Trockel W. (Eds). Economic Essays: A Festschrift for Werner Hildenbrand (2001), Springer, New York 181-200
16. Hart S., and Mas-Colell A. Uncoupled dynamics cannot lead to Nash equilibrium. Amer. Econ. Rev. 93 (2003) 1830-1836
17. Hofbauer, J., 1995. Stability for the best response dynamics. Techical report. Institut für Mathematik, Universität Wien, Strudlhofgasse 4, A-1090 Vienna, Austria
18. Hofbauer J., and Hopkins E. Learning in perturbed asymmetric games. Games Econ. Behav. 52 (2005) 133-152
19. Hofbauer J., and Sandholm W.H. On the global convergence of stochastic fictitious play. Econometrica 70 (2002) 2265-2294
20. Hofbauer J., and Sigmund K. Evolutionary Games and Population Dynamics (1998), Cambridge Univ. Press
21. Hopkins E., and Posch M. Attainability of boundary points under reinforcement learning. Games Econ. Behav. 44 (2005) 459-514
22. Leslie, D.S., 2003. Reinforcement learning in games. Ph.D. thesis. University of Bristol
23. Leslie D.S., and Collins E.J. Convergent multiple-timescales reinforcement learning algorithms in normal form games. Ann. Appl. Probability 13 (2003) 1231-1251
24. Leslie D.S., and Collins E.J. Individual Q-learning in normal form games. SIAM J. Control Optim 44 (2005) 459-514
25. Miyasawa, K., 1961. On the convergence of the learning process in a 2 × 2 non-zero-sum two-person game. Research Memorandum 33. Econometric Research Program, Princeton University, Princeton
26. Monderer D., and Shapley L.S. Fictitious play property for games with identical interests. J. Econ. Theory 68 (1996) 258-265
27. Robinson J. An iterative method of solving a game. Ann. Math. 54 (1951) 296-301
28. Roth A.E., and Erev I. Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term. Games Econ. Behav. 8 (1995) 164-212
29. Singh S., Jaakkola T., Littman M.L., and Szepesvari C. Convergence results for single-step on-policy reinforcement-learning algorithms. Machine Learning 38 (2000) 287-308
30. Sutton R.S., and Barto A.G. Reinforcement Learning: An Introduction (1998), MIT Press, Cambridge, MA
31. Taylor P.D., and Jonker L.D. Evolutionarily stable strategies and game dynamics. Math. Biosc. 40 (1978) 145-146
32. Van der Genugten B. A weakened form of fictitious play in two-person zero-sum games. Int. Game Theory Rev. 2 (2000) 307-328
33. Vrieze O.J., and Tijs S.H. Fictitious play applied to sequences of games and discounted stochastic games. Int. J. Game Theory 11 (1982) 71-85