Reinforcement Learning with Restrictions on the Action Set

DOI10.1137/130936488zbMath1382.91018arXiv1306.2918OpenAlexW2269850137MaRDI QIDQ2810060

Mathieu Faure, Mario Bravo

Publication date: 31 May 2016

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1306.2918

zbMATH Keywords

reinforcement learningstochastic approximationslearning in gamesbest-response dynamics

Mathematics Subject Classification ID

2-person games (91A05) Stability of topological dynamical systems (37B25) Stochastic approximation (62L20) Rationality and learning in game theory (91A26) Multistage and repeated games (91A20)

Related Items (2)

Robustness Properties in Fictitious-Play-Type Algorithms ⋮ \(\mathcal{H}_\infty\) tracking learning control for discrete-time Markov jump systems: a parallel off-policy reinforcement learning

This page was built for publication: Reinforcement Learning with Restrictions on the Action Set