Reinforcement Learning: Stochastic Approximation Algorithms for Markov Decision Processes
Optimization and Control
2015-12-25 v1
Abstract
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.
Cite
@article{arxiv.1512.07669,
title = {Reinforcement Learning: Stochastic Approximation Algorithms for Markov Decision Processes},
author = {Vikram Krishnamurthy},
journal= {arXiv preprint arXiv:1512.07669},
year = {2015}
}