Artículo de revista
Reinforcement learning with restrictions on the action set
Fecha
2015Registro en:
SIAM J. CONTROL OPTIM. Vol. 53, No. 1, pp. 287–312
DOI: 10.1137/130936488
Autor
Bravo, Mario
Faure, Mathieu
Institución
Resumen
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.