Coordination in multiagent reinforcement learning systems by virtual reinforcement signals

Authors:
M. A. S. Kamal;Junichi Murata
Affiliations:
(Correspd. Tel.: +603 6196 4417/ Fax: +603 6196 4433/ E-mail: maskamal@ieee.org) Department of Mechatronics Engineering, International Islamic University Malaysia, PO Box 10, 50728 Kuala Lumpur, M ...;Department of Electrical and Electronic Systems Engineering, Kyushu University, 744 Motooka, Nishi-Ku, Fukuoka 819-0395, Japan
Venue:
International Journal of Knowledge-based and Intelligent Engineering Systems
Year:
2007

Citing 13
Cited 1

Technical Note: \cal Q-Learning

Machine Learning
The evolution of strategies for multiagent environments

Adaptive Behavior
Learning to coordinate without sharing information

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Learning to solve Markovian decision processes

Learning to solve Markovian decision processes
Incremental evolution of complex general behavior

Adaptive Behavior - Special issue on environment structure and behavior
Multi-agent reinforcement learning in Markov games

Multi-agent reinforcement learning in Markov games
Multiagent systems: a modern approach to distributed artificial intelligence

Multiagent systems: a modern approach to distributed artificial intelligence
Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments

Machine Learning
Elevator Group Control Using Multiple Reinforcement Learning Agents

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Learning Situation-Specific Coordination in Cooperative Multi-agent Systems

Autonomous Agents and Multi-Agent Systems
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Multiagent reinforcement learning using function approximation

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Reinforcement learning coordination with combined heuristics in multi-agent environment for university timetabling

Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel method for on-line coordination in multiagent reinforcement learning systems. In this method a reinforcement-learning agent learns to select its action estimating system dynamics in terms of both the natural reward for task achievement and the virtual reward for cooperation. The virtual reward for cooperation is ascertained dynamically by a coordinating agent who estimates it from the change in degree of cooperation of all agents using a separate reinforcement learning. This technique provides adaptive coordination, requires less communication and ensures agents to be cooperative. The validity of virtual rewards for convergence in learning is verified, and the proposed method is tested on two different simulated domains to illustrate its significance. The empirical performance of the coordinated system compared to the uncoordinated system illustrates its advantages for multiagent systems.