Levels of realism for cooperative multi-agent reinforcement learning
ICSI'12 Proceedings of the Third international conference on Advances in Swarm Intelligence - Volume Part I
Non-reciprocating Sharing Methods in Cooperative Q-Learning Environments
WI-IAT '12 Proceedings of the The 2012 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology - Volume 02
| Hi-index | 0.00 |
This article proposes and compares different interac-tion models for reinforcement learning based on multi-agent system. The cooperation during the learning proc-ess is crucial to guarantee the convergence to a good policy. The exchange of rewards among the agents during the interaction is a complex task and if it is inadequate it may cause delays in learning or generate unexpected transitions, making the cooperation inefficient and con-verging to a non-satisfactory policy. In order to allow the interactive discovery of high quality policies we have developed several cooperation models based on the ex-change of action policies between the agents. Experimen-tal results have shown that the proposed cooperation models are able to speed up the convergence of the agents while achieving optimal action policies even in high-dimensional environments (e.g. traffic), outperforming the standard Q-learning algorithm.