Abstract | ||
---|---|---|
Multiagent learning attracts much attention in the past few years as it poses very challenging problems. Reinforce- ment 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 pro- poses 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, get- ting promising results. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/ICTAI.2007.15 | Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference |
Keywords | Field | DocType |
Markov processes,decision theory,learning (artificial intelligence),multi-agent systems,Markov decision process,multiagent reinforcement learning,predator-prey domain,voting process | Robot learning,Instance-based learning,Active learning (machine learning),Voting,Computer science,Markov decision process,Multi-agent system,Decision theory,Artificial intelligence,Machine learning,Reinforcement learning | Conference |
Volume | ISSN | ISBN |
2 | 1082-3409 | 978-0-7695-3015-4 |
Citations | PageRank | References |
6 | 0.64 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ioannis Partalas | 1 | 378 | 24.44 |
Ioannis Feneris | 2 | 6 | 0.64 |
Ioannis Vlahavas | 3 | 1596 | 79.02 |