Reinforcement learning with restrictions on the action set
Author
Abstract
Consider a two-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 actions 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.
General note
Artículo de publicación ISI
Patrocinador
Fondecyt grant
3130732
Nucleo Milenio Informacion y Coordinacion en Redes
ICM/FIC P10-024F
Complex Engineering Systems Institute
ICM: P-05-004-F
CONICYT: FBO16
Quote Item
SIAM J. CONTROL OPTIM. Vol. 53, No. 1, pp. 287–312
Collections
The following license files are associated with this item: