doi: 10.4304/jsw.9.3.634-640
Statistics Based Q-learning Algorithm for Multi-Agent System and Application in RoboCup
- Hunan Institute of Engineering, Xiangtan, China
Abstract
This paper proposes statistic learning basedQ-learning algorithm for Multi-Agent System, theagent can learn other agents’ action policies throughobserving and counting the joint action, a concise butuseful hypothesis is adopted to denote the optimalpolicies of other agents, the full joint probability ofpolicies distribution guarantees the optimal actionchoice to the learning agent. The algorithm can alsoimprove the learning speed because the conventionalQ-learning space is cut from exponential one to linearone. The convergence of the algorithm has been proved;the successful application of this algorithm in theRoboCup shows its good learning performance.
Keywords
- Q-learning
- Statistics
- Multi-agent
- Rob
How to Cite
Ya Xie and Zhonghua Huang, "Statistics Based Q-learning Algorithm for Multi-Agent System and Application in RoboCup," Journal of Software, vol. 9, no. 3, pp. 634-640, 2014. https://doi.org/ 10.4304/jsw.9.3.634-640
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).