Learning to Cooperate via Policy Search

Learning to Cooperate via Policy Search (2000)

Cached

Download Links

[www.ai.mit.edu]
[www.ai.mit.edu]

Other Repositories/Bibliography

DBLP

by Leonid Peshkin , Kee-eung Kim

Citations:

114 - 4 self

Versions

Version History

Metadata Version 2

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Learning to Cooperate via Policy Search	user correction - Legacy Corrections
AUTHOR NAME	Leonid Peshkin	SVM HeaderParse 0.1
AUTHOR AFFIL	MIT AI Laboratory	SVM HeaderParse 0.2
AUTHOR ADDR	545 Technology Square; Cambridge, MA 02139	SVM HeaderParse 0.1
AUTHOR NAME	Kee-eung Kim	SVM HeaderParse 0.1
AUTHOR AFFIL	Computer Science Dept.; Brown University	SVM HeaderParse 0.2
AUTHOR ADDR	Box 1910; Providence, RI 02906	SVM HeaderParse 0.1
ABSTRACT	Cooperative games are those in which both agents share the same payoff structure. Valuebased reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the game state is completely observable to both agents. Policy search methods are a reasonable alternative to value-based methods for partially observable environments. In this paper, we provide a gradient-based distributed policysearch method for cooperative games and compare the notion of local optimum to that of Nash equilibrium. We demonstrate the effectiveness of this method experimentally in a small, partially observable simulated soccer domain. 1 INTRODUCTION The interaction of decision makers who share an environment is traditionally studied in game theory and economics. The game theoretic formalism is very general, and analyzes the problem in terms of solution concepts such as Nash equilibrium [12], but usually works under the assu...	user correction - Legacy Corrections
YEAR	2000	user correction - Legacy Corrections
CITATIONS	20 found	ParsCit 1.0