Reinforcement learning with restrictions on the action set - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2013

Reinforcement learning with restrictions on the action set

Résumé

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.
Fichier principal
Vignette du fichier
bf13_HAL.pdf (280.22 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00832599 , version 1 (12-06-2013)

Identifiants

Citer

Mario Bravo, Mathieu Faure. Reinforcement learning with restrictions on the action set. 2013. ⟨hal-00832599⟩
217 Consultations
148 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More