Reinforcement Learning Algorithms for MDPs
Published Online: 15 FEB 2011
Copyright © 2010 John Wiley & Sons, Inc. All rights reserved.
Wiley Encyclopedia of Operations Research and Management Science
How to Cite
Szepesvári, C. 2011. Reinforcement Learning Algorithms for MDPs. Wiley Encyclopedia of Operations Research and Management Science. .
- Published Online: 15 FEB 2011
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations. In this article we focus on a few selected algorithms of reinforcement learning which build on the powerful theory of dynamic programming.
- reinforcement learning;
- Markov Decision Processes;
- temporal difference learning;
- stochastic approximation;
- function approximation;
- least-squares methods;
- actor-critic methods;
- policy gradient;
- natural gradient