Learning cooperation from classifier systems

Authors:
Trung Hau Tran;Cédric Sanza;Yves Duthen
Affiliations:
Paul Sabatier University – Toulouse III, Toulouse, France;Paul Sabatier University – Toulouse III, Toulouse, France;Paul Sabatier University – Toulouse III, Toulouse, France
Venue:
CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Year:
2005

Citing 7
Cited 0

Behavior-based robot navigation for extended domains

Adaptive Behavior
Using genetic algorithms to learn reactive control parameters for autonomous robotic navigation

Adaptive Behavior
Coordination Developed by Learning from Evaluations

Collaboration between Human and Artificial Societies, Coordination and Agent-Based Distributed Computing
Multi-Agent Coordination by Communication of Evaluations

Proceedings of the 8th European Workshop on Modelling Autonomous Agents in a Multi-Agent World: Multi-Agent Rationality
Communication and Interaction with Learning Agents in Virtual Soccer

VW '00 Proceedings of the Second International Conference on Virtual Worlds
COOPERATIVE COEVOLUTION OF MULTI-AGENT SYSTEMS

COOPERATIVE COEVOLUTION OF MULTI-AGENT SYSTEMS
Classifier fitness based on accuracy

Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with cooperation for virtual reality applications. In a multi-agent system, cooperation between agents is an important element to solve a common task, which is very difficult or impossible for a single agent or a group of agents without cooperation. Hence we focus on cooperation in the predator-prey problem where a group of programmed and learning predators coordinates their actions to capture the prey. These actions of a learning predator are dynamically weighted by a behavioral system based on motor schemas and classifier systems. At each instant, the system must modify the weights in order to enhance the strategies of the group, as surrounding a prey. Thanks to the classifier system the learning predator learns situations and gradually adapts its actions to its environment. First encouraging results show that coupling such systems gives very efficient performances in dynamic environments.