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...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Information sciences Ročník 261; s. 1 - 31
Hlavní autori: Xu, Xin, Zuo, Lei, Huang, Zhenhua
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Inc 10.03.2014
Predmet:
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
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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