On the convergence of reinforcement learning
- 1 May 2005
- journal article
- Published by Elsevier in Journal of Economic Theory
- Vol. 122 (1) , 1-36
- https://doi.org/10.1016/j.jet.2004.03.008
Abstract
No abstract availableKeywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Two Competing Models of How People Learn in GamesEconometrica, 2002
- A Simple Adaptive Procedure Leading to Correlated EquilibriumEconometrica, 2000
- Vertex-Reinforced Random Walk on Z Has Finite RangeThe Annals of Probability, 1999
- Dynamics of stochastic approximation algorithmsPublished by Springer Nature ,1999
- Adaptive Learning with Nonlinear Dynamics Driven by Dependent ProcessesEconometrica, 1994
- On designing economic agents that behave like human agentsJournal of Evolutionary Economics, 1993
- Nonconvergence to Unstable Points in Urn Models and Stochastic ApproximationsThe Annals of Probability, 1990
- Learning the evolutionarily stable strategyJournal of Theoretical Biology, 1981
- A Strong Law for Some Generalized Urn ProcessesThe Annals of Probability, 1980
- Bernard Friedman's UrnThe Annals of Mathematical Statistics, 1965