arXiv:1512.07669 Abstract | arXiv Analytics

arXiv:1512.07669 [math.OC]Abstract References Reviews Resources

Reinforcement Learning: Stochastic Approximation Algorithms for Markov Decision Processes

Published 2015-12-23Version 1

This article presents a short and concise description of stochastic approximation algorithms in reinforcement learning of Markov decision processes. The algorithms can also be used as a suboptimal method for partially observed Markov decision processes.

Categories: math.OC

Keywords: markov decision processes, stochastic approximation algorithms, reinforcement learning, concise description, suboptimal method

Related articles: Most relevant | Search more

arXiv:1901.07839 [math.OC] (Published 2019-01-23)

Reinforcement Learning of Markov Decision Processes with Peak Constraints

Ather Gattami

arXiv:1911.05578 [math.OC] (Published 2019-11-13)

Reachability and safety objectives in Markov decision processes on long but finite horizons

Galit Ashkenazi-Golan, János Flesch, Arkadi Predtetchinski, Eilon Solan

arXiv:1809.06277 [math.OC] (Published 2018-09-17)

Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate

Adithya M. Devraj, Ana Bušić, Sean Meyn

arXiv Analytics

arXiv:1512.07669 [math.OC]Abstract References Reviews Resources

Reinforcement Learning: Stochastic Approximation Algorithms for Markov Decision Processes

Links

Toolbox

arXiv:1512.07669 [math.OC]AbstractReferencesReviewsResources

Reinforcement Learning: Stochastic Approximation Algorithms for Markov Decision Processes

Links

Toolbox

arXiv:1512.07669 [math.OC]Abstract References Reviews Resources