An Improved Multiagent Reinforcement Learning Algorithm

Authors:
Xiangping Meng;Robert Babuska;Lucian Busoniu;Yu Chen;Wanyu Tan
Affiliations:
Department of Electrical Engineering, Changchun Institute of Technology, P. R. China;Delft Center for Systems and Control, Delft University of Technology, The Netherlands;Delft Center for Systems and Control, Delft University of Technology, The Netherlands;Department of Computer Engineering,Northeast China Institute of Electric Power, P.R.China;Department of Electrical Engineering, Changchun Institute of Technology, P. R. China
Venue:
IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Year:
2005

Citing 0
Cited 2

COOPERATIVE LEARNING BY POLICY-SHARING IN MULTIPLE AGENTS

Cybernetics and Systems
Distributed Reinforcement Learning for Coordinate Multi-Robot Foraging

Journal of Intelligent and Robotic Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

An improved reinforcement learning algorithm is proposed in this paper. This algorithm is based on linear programming method for finding the best-response policy. A pursuit example is tested and the results show that this algorithm has some properties, such as easy computation, simple operation procedure and can guarantee an good learning convergence.