Paper Title:
Multi-Agent Reinforcement Learning Based on K-Means Clustering in Multi-Robot Cooperative Systems
  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.

  Info
Periodical
Edited by
Yuhang Yang, Xilong Qu, Yiping Luo and Aimin Yang
Pages
75-80
DOI
10.4028/www.scientific.net/AMR.216.75
Citation
C. A. Liu, F. Liu, C. Y. Liu, H. Wu, "Multi-Agent Reinforcement Learning Based on K-Means Clustering in Multi-Robot Cooperative Systems", Advanced Materials Research, Vol. 216, pp. 75-80, 2011
Online since
March 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Chang Hui Yang
Abstract:In the multi-agent supply chain of manufacturing enterprise, there is the problem that purchasing agent need negotiate with supplier agent...
608
Authors: Yan Gao
Abstract:For poor accuracy of detection of the urban traffic network classification, the Support Vector Machine (SVM)is applied to classification of...
489
  | Authors: Bo Yu, Zi Xian Zhang, Yi Xiong Feng, Luis Ariel Diago, Ichiro Hagiwara
Chapter 1: Engineering Applications
Abstract:Over the past decades, Distributed Systems (DS) have been adopted for industrial applications to improve the system efficiency because...
16
Authors: Ding Cai Huang, Xiang Ke Wang, Yi Feng Niu
Chapter 4: System Modeling and Algorithms for Intelligent Automation and Control Systems
Abstract:The cooperative output regulation problem for a class of nonlinear uncertain multi-agent systems is considered. Based on the distributed...
238
Authors: Mirosław Mrozek
Chapter 3: Advanced Methods for Control Systems and Robotics
Abstract:Multi-agent systems are used mainly in IT solutions and control groups of robots. From the point of view of classical control architectures,...
183