Reinforcement learning algorithms with function approximation: Recent advances and applications

In recent years, the research on reinforcement learning (RL) has focused on function approximation in learning prediction and control of Markov decision processes (MDPs). The usage of function approximation techniques in RL will be essential to deal with MDPs with large or continuous state and actio...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences Vol. 261; pp. 1 - 31
Main Authors: Xu, Xin, Zuo, Lei, Huang, Zhenhua
Format: Journal Article
Language:English
Published: Elsevier Inc 10.03.2014
Subjects:
Approximate dynamic programming
Function approximation
Generalization
Learning control
Reinforcement learning
Approximate dynamic programming
Function approximation
Learning control
Generalization
Reinforcement learning
ISSN:0020-0255, 1872-6291
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, the research on reinforcement learning (RL) has focused on function approximation in learning prediction and control of Markov decision processes (MDPs). The usage of function approximation techniques in RL will be essential to deal with MDPs with large or continuous state and action spaces. In this paper, a comprehensive survey is given on recent developments in RL algorithms with function approximation. From a theoretical point of view, the convergence and feature representation of RL algorithms are analyzed. From an empirical aspect, the performance of different RL algorithms was evaluated and compared in several benchmark learning prediction and learning control tasks. The applications of RL with function approximation are also discussed. At last, future works on RL with function approximation are suggested.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2013.08.037