Reference
L. Buşoniu, D. Ernst, B. De Schutter, and R. Babuška,
"Approximate reinforcement learning: An overview,"
Proceedings
of the 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement
Learning (ADPRL 2011), Paris, France, pp. 1-8, Apr. 2011.
Abstract
Reinforcement learning (RL) allows agents to learn how to optimally interact
with complex environments. Fueled by recent advances in approximation-based
algorithms, RL has obtained impressive successes in robotics, artificial
intelligence, control, operations research, etc. However, the scarcity of
survey papers about approximate RL makes it difficult for newcomers to grasp
this intricate field. With the present overview, we take a step toward
alleviating this situation. We review methods for approximate RL, starting from
their dynamic programming roots and organizing them into three major classes:
approximate value iteration, policy iteration, and policy search. Each class is
subdivided into representative categories, highlighting among others offline
and online algorithms, policy gradient methods, and simulation-based
techniques. We also compare the different categories of methods, and outline
possible ways to enhance the reviewed algorithms.
Downloads
BibTeX
@inproceedings{BusMun:11-008,
author = {Bu{\c{s}}oniu, Lucian and Ernst, Damien and De Schutter, Bart
and Babu{\v{s}}ka, Robert},
title = {Approximate Reinforcement Learning: {An} Overview},
booktitle = {Proceedings of the 2011 IEEE Symposium on Adaptive Dynamic
Programming and Reinforcement Learning (ADPRL 2011)},
address = {Paris, France},
pages = {1--8},
month = apr,
year = {2011}
}