Reinforcement Learning with Restrictions on the Action Set

Mario Bravo () and Mathieu Faure ()
Additional contact information
Mario Bravo: Instituto de Sistemas Complejos de Ingenieria (ISCI), Universidad de Chile

No 1335, AMSE Working Papers from Aix-Marseille School of Economics, France

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: Reinforcement learning; fictitious play; Markovian procedures. (search for similar items in EconPapers)
Pages: 29 pages
Date: 2013-07-01, Revised 2013-07-01
New Economics Papers: this item is included in nep-gth, nep-hpe and nep-mic
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.amse-aixmarseille.fr/sites/default/file ... trictions-action-set (application/pdf)

Related works:
Working Paper: Reinforcement Learning with Restrictions on the Action Set (2015)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aim:wpaimx:1335

Access Statistics for this paper

More papers in AMSE Working Papers from Aix-Marseille School of Economics, France AMU-AMSE - 5-9 Boulevard Maurice Bourdet, CS 50498 - 13205 Marseille Cedex 1. Contact information at EDIRC.
Bibliographic data for series maintained by Gregory Cornu ().