On the convergence of reinforcement learning

Journal of Economic Theory

Volumn 122, Issue 1, 2005, Pages 1-36

  Beggs, Alan W ^a  

^a WADHAM COLLEGE   (United Kingdom)

Author keywords

Games; Reinforcement learning

Indexed keywords

EID: 16244410118     PISSN: 00220531     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jet.2004.03.008     Document Type: Article

References (39)

1. W.B. Arthur On designing economic agents that behave like human agents J. Evolutionary Econ. 3 1993 1-22
2. P. Auer, N. Cesa-Bianchi, Y. Freund, R. Schapire, Gambling in a rigged casino: The adversarial multi-armed bandit problem, Mimeo, AT&T laboratories, 1998.
3. M. Benaïm, Dynamics of stochastic approximation algorithms, in: Seminaire de Probabilités, XXXIII, Lecture Notes in Mathematics, vol. 1709, Springer, Berlin, 1999, pp. 1-68.
4. M. Benaïm M. Hirsch Mixed equilibria and dynamical systems arising from fictitious play in perturbed games Games Econ. Behav. 29 1999 36-72
5. A. Benveniste M. Metivier P. Priouret Adaptive Algorithms and Stochastic Approximation 1990 Springer Berlin, New York
6. J. Bjornerstedt J. Weibull Nash equilibrium and evolution by imitation in: K. Arrow et al. (Eds.) The Rational Foundations of Economic Behaviour 1996 Macmillan London pp. 155-171
7. T. Börgers R. Sarin Learning through reinforcement and replicator dynamics J. Econ. Theory 77 1997 1-14
8. O. Brandiere M. Duflo Les algorithmes stochastiques contournent-ils les pieges Ann. Inst. Henri Poincare 32 1996 395-427
9. C. Camerer T.-H. Ho Experience-weighted attraction learning in normal form games Econometrica 67 1999 827-874
10. H.-F. Chen Convergence rate of stochastic algorithms in degenerate cases SIAM J. Control Optim. 36 1998 100-114
11. M. Duflo Algorithmes Stochastiques 1996 Springer Berlin
12. M. Duflo Random Iterative Models 1997 Springer Berlin
13. P. Dupuis H. Kushner Stochastic approximations and large deviations : Upper bounds and w.p.1 convergence SIAM J. Control Optim. 27 1989 1108-1135
14. I. Erev A. Roth Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria Amer. Econ. Rev. 88 1998 848-881
15. D. Freedman Bernard friedman's urn Ann. Math. Statist. 36 1965 956-970
16. D. Fudenberg D. Levine Learning and the Theory of Games 1998 MIT Press Cambridge, MA
17. J. Gale K. Binmore L. Samuelson Learning to be imperfect: The ultimatum game Games Econ. Behav. 8 1995 56-90
18. J. Hale Ordinary Differential Equations 1980 Robert E. Krieger Publishing Co. Huntingdon, New York
19. P. Hall C. Heyde Martingale Limit Theory and its Applications 1980 Academic Press New York
20. C. Harley Learning the evolutionarily stable strategy J. Theoret. Biol. 89 1981 611-633
21. S. Hart A. Mas-Collel A simple adaptive procedure leading to correlated equilibrium Econometrica 68 2000 1127-1150
22. S. Hart A. Mas-Collel A general class of adaptive strategies J. Econ. Theory 98 2001 26-54
23. S. Hart, A. Mas-Collel, A reinforcement procedure leading to correlated equilibrium, Mimeo, Hebrew University, 2001.
24. B. Hill D. Lane W. Sudderth A strong law for some generalized urn processes Ann. Probab. 8 1980 214-226
25. J. Hofbauer K. Schlag Sophisticated imitation in cyclic games J. Evolutionary Econ. 10 2000 523-543
26. J. Hofbauer K. Sigmund The Theory of Evolution and Dynamical Systems 1988 Cambridge University Press Cambridge
27. E. Hopkins Two competing models of how people learn in games Econometrica 70 2001 2141-2166
28. A. Ianni, Reinforcement learning and the power law of practice, Mimeo, University of Southampton, 2001.
29. S. Karlin, Mathematical Methods and Theory in Games, Programming and Economics, vol. I, Addison-Wesley, Reading, MA, 1959.
30. C.-M. Kuan H. White Adaptive learning with nonlinear dynamics driven by dependent processes Econometrica 62 1994 1087-1114
31. H. Kushner G. Yin Stochastic Approximation Algorithms and Applications 1997 Springer New York
32. J.-F. Laslier R. Topol B. Walliser A behaviorial learning process in games Games Econ. Behav. 37 2001 340-366
33. J. Maynard Smith Evolution and the Theory of Games 1982 Cambridge University Press Cambridge
34. R. Pemantle Nonconvergence to unstable points in urn models and stochastic approximations Ann. Probab. 18 1990 698-712
35. R. Pemantle S. Volkov Vertex-reinforced random walk on z has finite range Ann. Probab. 27 1999 1368-1388
36. M. Posch Cycling in a stochastic learning algorithm for normal form games J. Evolutionary Econ. 7 1997 193-207
37. A. Roth I. Erev Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term Games Econ. Behav. 8 1995 164-212
38. A. Rustichini Optimal properties of stimulus-response learning models Games Econ. Behav. 29 1999 244-273
39. B. Skyrms R. Pemantle A dynamic model of social network formation Proc. Nat. Acad. Sci. 97 2000 9340-9346