Evolutionary game theory and multi-agent reinforcement learning

被引：83
作者：
Tuyls, K [1 ]
Nowé, A
机构：
[1] Univ Maastricht, Inst Knowledge & Agent Technol, Maastricht, Netherlands
[2] Univ Virginia, Computat Modeling Lab, Brussels, Belgium
来源：
KNOWLEDGE ENGINEERING REVIEW | 2005年 / 20卷 / 01期
关键词：
D O I：
10.1017/S026988890500041X
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we survey the basics of reinforcement learning and (evolutionary) game theory, applied to the field of multi-agent systems. This paper contains three parts. We start with an overview on the fundamentals of reinforcement learning. Next we summarize the most important aspects of evolutionary game theory. Finally, we discuss the state-of-the-art of multi-agent reinforcement learning and the mathematical connection with evolutionary game theory.
引用
收藏
页码：63 / 90
页数：28
相关论文
共 61 条
[21]  
KAPETANAKIS S, 2002, REINFORCEMENT LEARNI
[22]  
KONONEN V, 2004, THESIS HELSINKI U TE
[23]  
Littman M. L., 1994, MACHINE LEARNING P 1, P157, DOI 10.1016/B978-1-55860-335-6.50027-1
[24]  
Loch J., 1998, P 15 INT C MACH LEAR
[25]  
MAARTEN P, 2003, STUDY REINFORCEMENT
[26]  
MAYNARDSMITH J, 1982, EVOLUTION THEORY TAM
[27]  
MUKHERJEE R, 2001, 5 C AUT AG, P21
[28]  
Narendra K. S., 1989, LEARNING AUTOMATA IN
[29]   LEARNING AUTOMATA - SURVEY [J].
NARENDRA, KS ;
THATHACHAR, MA .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1974, SMC4 (04) :323-334
[30]  
NOWE A, 2001, P 12 EUR C MACH LEAR, P382
1234567