Abstract | ||
---|---|---|
Multiagent learning is a challenging problem in the area of multiagent systems because of the non-stationary environment caused by the interdependencies between agents. Learning for coordination becomes more difficult when agents do not know the structure of the environment and have only local observability. In this paper, an approach is proposed to enable autonomous agents to learn where and how to coordinate their behaviours in an environment where the interactions between agents are sparse. Our approach firstly adopts a statistical method to detect those states where coordination is most necessary. A Q-learning based coordination mechanism is then applied to coordinate agents' behaviours based on their local observability of the environment. We test our approach in grid world domains to show its good performance. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-25832-9_40 | Australasian Conference on Artificial Intelligence |
Keywords | Field | DocType |
non-stationary environment,multiagent learning,sparse interaction,coordination mechanism,local observability,good performance,autonomous agent,multiagent system,challenging problem,coordinated learning,grid world domain,approach firstly | Interdependence,Observability,Autonomous agent,Computer science,Multi-agent system,Multiagent learning,Artificial intelligence,Grid | Conference |
Volume | ISSN | Citations |
7106 | 0302-9743 | 2 |
PageRank | References | Authors |
0.37 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chao Yu | 1 | 91 | 12.97 |
Minjie Zhang | 2 | 267 | 27.71 |
Fenghui Ren | 3 | 153 | 20.05 |