A Survey on Multiagent Reinforcement Learning Towards Multi-Robot Systems

Abstract- Multiagent reinforcement learning for multirobot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theoretical research and practical applications, currently there have been a lot of efforts towards providing some solutions to this challenge. However, there are still many difficulties in scaling up multiagent reinforcement learning to multi-robot systems. The main objective of this paper is to provide a survey on multiagent reinforcement learning in multi-robot systems, based on the literature the authors collected. After reviewing some important advances in this field, some challenging problems are analyzed. A concluding remark is made from the perspectives of the authors.

• Type: Conference
• Year: 2005
• Where: CIG
• Authors: Erfu Yang, Dongbing Gu
• Keywords: Applied Computing, CIG 2005, Multi-robot Systems, Multiagent Reinforcement, Reinforcement Learning