Title: Multi-robot systems with agent-based reinforcement learning: evolution, opportunities and challenges

Authors: Erfu Yang, Dongbing Gu

Addresses: School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK. ' School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK

Abstract: Multi-agent reinforcement learning for multi-robot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theoretical researches and practical applications, currently there have been a lot of efforts towards providing good solutions to this challenge. However, there are still many difficulties in scaling up multi-agent reinforcement learning to multi-robot systems. This paper presents a survey on the evolution, opportunities and challenges of applying agent-based reinforcement learning to multi-robot systems. After reviewing some important advances in this field, some challenging problems and promising research directions are focused on. A concluding remark is made from the perspectives of the authors.

Keywords: multi-robot systems; MRSs; reinforcement learning; multi-agent systems; MAS; stochastic games; approximation; generalisation; fuzzy logic; survey; multiple robots; agent-based systems.

DOI: 10.1504/IJMIC.2009.024735

International Journal of Modelling, Identification and Control, 2009 Vol.6 No.4, pp.271 - 286

Published online: 29 Apr 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article