Nonconvergence to saddle boundary points under perturbed reinforcement learning

Authors Georgios C. Chasparis
Jeff Shamma
Anders Rantzer
Editors
Title Nonconvergence to saddle boundary points under perturbed reinforcement learning
Type article
Journal International Journal of Game Theory
Number 3
Volume 44
DOI 10.1007/s00182-014-0449-3
ISSN 0020-7276 (Print) 1432-1270 (Online)
Month August
Year 2015
Pages 667-699
SCCH ID# 1359
Abstract

For several reinforcement learning models in strategic-form games, convergence to action profiles that are not Nash equilibria may occur with positive probability under certain conditions on the payoff function. In this paper, we explore how an alternative reinforcement learning model, where the strategy of each agent is perturbed by a strategy-dependent perturbation (or mutations) function, may exclude convergence to non-Nash pure strategy profiles. This approach extends prior analysis on reinforcement learning in games that addresses the issue of convergence to saddle boundary points. It further provides a framework under which the effect of mutations can be analyzed in the context of reinforcement learning.