Learning in games via reinforcement learning and regularization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Mathematics of Operations Research Year : 2016

Learning in games via reinforcement learning and regularization

Abstract

We investigate a class of reinforcement learning dynamics in which each player plays a "regularized best response" to a score vector consisting of his actions' cumulative payoffs. Regularized best responses are single-valued regularizations of ordinary best responses obtained by maximizing the difference between a player's expected cumulative payoff and a (strongly) convex penalty term. In contrast to the class of smooth best response maps used in models of stochastic fictitious play, these penalty functions are not required to be infinitely steep at the boundary of the simplex; in fact, dropping this requirement gives rise to an important dichotomy between steep and nonsteep cases. In this general setting, our main results extend several properties of the replicator dynamics such as the elimination of dominated strategies, the asymptotic stability of strict Nash equilibria and the convergence of time-averaged trajectories to interior Nash equilibria in zero-sum games.
Fichier principal
Vignette du fichier
1407.6267v1.pdf (1.6 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01073491 , version 1 (06-01-2015)

Identifiers

Cite

Panayotis Mertikopoulos, William H. Sandholm. Learning in games via reinforcement learning and regularization. Mathematics of Operations Research, 2016, 41 (4), pp.1297-1324. ⟨10.1287/moor.2016.0778⟩. ⟨hal-01073491⟩
275 View
481 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More