Multiagent learning using a variable learning rate


Learning to act in a multiagent environment is a difficult problem since the normal definition of an optimal policy no longer applies. The optimal policy at any moment depends on the policies of the other agents. This creates a situation of learning a moving target. Previous learning algorithms have one of two shortcomings depending on their approach. They… (More)
DOI: 10.1016/S0004-3702(02)00121-2


14 Figures and Tables


Citations per Year

597 Citations

Semantic Scholar estimates that this publication has 597 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Bowling2002MultiagentLU, title={Multiagent learning using a variable learning rate}, author={Michael H. Bowling and Manuela M. Veloso}, journal={Artif. Intell.}, year={2002}, volume={136}, pages={215-250} }