Reinforcement learning with restrictions on the action setReport as inadecuate

Reinforcement learning with restrictions on the action set - Download this document for free, or read online. Document in PDF available to download.

* Corresponding author 1 ISCI - Instituto de Sistemas Complejos de Ingeniería 2 GREQAM - Groupement de Recherche en Économie Quantitative d-Aix-Marseille

Abstract : Consider a 2-player normal-form game repeated over time. We introduce an adaptive learning procedure, where the players only observe their own realized payoff at each stage. We assume that agents do not know their own payoff function, and have no information on the other player. Furthermore, we assume that they have restrictions on their own action set such that, at each stage, their choice is limited to a subset of their action set. We prove that the empirical distributions of play converge to the set of Nash equilibria for zero-sum and potential games, and games where one player has two actions.

Keywords : Normal form games Learning Adaptive dynamics Stochastic approximation Non-homogeneous Markov chains

Author: Mario Bravo - Mathieu Faure -



Related documents