A convergent online single time scale actor critic algorithm

MaRDI QIDQ2896031zbMATH OpenFDO

Authors Dotan Di Castro, Ron Meir

Publication date 13 July 2012

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://www.jmlr.org/papers/v11/dicastro10a.html

zbMATH Keywords

actor criticsingle time scale convergencetemporal difference

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Recommendations

• Natural actor-critic algorithms
• OnActor-Critic Algorithms
• Actor-critic algorithms with online feature adaptation
• An actor-critic algorithm for constrained Markov decision processes
• An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes

Cited in

(6)

• Natural actor-critic algorithms
• Natural actor-critic based on batch recursive least-squares
• OnActor-Critic Algorithms
• Global convergence of policy gradient methods to (almost) locally optimal policies
• A Small Gain Analysis of Single Timescale Actor Critic
• On the sample complexity of actor-critic method for reinforcement learning with function approximation

This page was built for publication: A convergent online single time scale actor critic algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896031)