Fuzzy reinforcement learning for embedded soccer agents in a multi-agent context

Authors:
A. M. Tehrani;M. S. Kamel;A. M. Khamis
Affiliations:
Pattern Analysis and Machine Intelligence Lab, Electrical and Computer Engineering Department, University of Waterloo, Waterloo, ON, Canada;Pattern Analysis and Machine Intelligence Lab, Electrical and Computer Engineering Department, University of Waterloo, Waterloo, ON, Canada;Pattern Analysis and Machine Intelligence Lab, Electrical and Computer Engineering Department, University of Waterloo, Waterloo, ON, Canada
Venue:
International Journal of Robotics and Automation
Year:
2006

Citing 7
Cited 0

KQML as an agent communication language

CIKM '94 Proceedings of the third international conference on Information and knowledge management
Artificial intelligence: a modern approach

Artificial intelligence: a modern approach
Towards collaborative and adversarial learning:: a case study in robotic soccer

International Journal of Human-Computer Studies - Evolution and learning in multiagent systems
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Scaling Reinforcement Learning toward RoboCup Soccer

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
RoboCup: A Challenge Problem for AI and Robotics

RoboCup-97: Robot Soccer World Cup I
Dynamic balance of a biped robot using fuzzy reinforcement learning agents

Fuzzy Sets and Systems - Special issue: Fuzzy set techniques for intelligent robotic systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The work presented in this paper aims at combining fuzzy function approximation and reinforcement learning in order to create robotic soccer agents that are able to coordinate their behaviours locally and socially while learning from experience. This simultaneous coordination and learning ability can play a crucial role in improving the behaviour usage of robotic soccer agents. To achieve this goal, a fuzzy reinforcement learning technique for a single agent is first examined and then this technique is applied to multiple agents. The conducted experiments through a soccer simulation system show that the performance of robot scoring speed is improved using the proposed approach.