Multi-Agent Reinforcement Learning Based on K-Means Clustering in Multi-Robot Cooperative Systems
- 1 March 2011
- journal article
- Published by Trans Tech Publications, Ltd. in Advanced Materials Research
- Vol. 216, 75-80
- https://doi.org/10.4028/www.scientific.net/amr.216.75
Abstract
To solve the curse of dimensionality problem in multi-agent reinforcement learning, a learning method based on k-means is presented in this paper. In this method, the environmental state is represented as key state factors. The state space explosion is avoided by classifying states into different clusters using k-means. The learning rate is improved by assigning different states to existent clusters, as well as corresponding strategy. Compared to traditional Q-learning, our experimental results of the multi-robot cooperation show that our scheme improves the team learning ability efficiently. Meanwhile, the cooperation efficiency can be enhanced successfully.Keywords
This publication has 9 references indexed in Scilit:
- On Experiences in a Complex and Competitive Gaming Domain: Reinforcement Learning Meets RoboCupPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Game Theory As A Tool To Strategize As Well As Predict Nodes Behavior In Peer-to-Peer NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient Solution Algorithms for Factored MDPsJournal of Artificial Intelligence Research, 2003
- An efficient k-means clustering algorithm: analysis and implementationIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and ModelsJournal of Artificial Intelligence Research, 2002
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999
- Building agent teams using an explicit teamwork model and learningArtificial Intelligence, 1999
- Reinforcement Learning: An IntroductionIEEE Transactions on Neural Networks, 1998
- Q-learningMachine Learning, 1992