LPIS Home Page
Google Search

Title: Multi-Agent Reinforcement Learning using Strategies and Voting
Author(s): I. Partalas, I. Feneris, I. Vlahavas.
Keywords: multi-agent, reinforcement learning, voting.
Appeared in: Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), (to be presented), IEEE, 2007.
Abstract: Multiagent learning attracts much attention in the past few years as it poses very challenging problems. Reinforcement Learning is an appealing solution to the problems that arise to Multi Agent Systems (MASs). This is due to the fact that Reinforcement Learning is a robust and well suited technique for learning in MASs. This paper proposes a multi-agent Reinforcement Learning approach, that uses coordinated actions, which we call strategies and a voting process that combines the decisions of the agents, in order to follow a strategy. We performed experiments to the predator-prey domain, comparing our approach with other multi-agent Reinforcement Learning techniques, getting promising results.
See also :

        This paper has been cited by the following:

1 Jin-Gang Cao, Research on electronic commerce automated negotiation in multi-agent system based on reinforcement learning, IEEE International Conference on Machine Learning and Cybernetics, pp. 1419 - 1423,2009.
2 Jin-gang Cao, Multi-agent Automated Negotiation Based on Reinforcement Learning in Electronic Commerce, 1(3) pp. 361-364,MASAUM Journal of Computing, 2009.