Proposal and Evaluation of an Action Selection Strategy with Expected Failure Probability in Multi-agent Learning
Kazuteru Miyazaki, Koudai Furukawa, Hiroaki Kobayashi · 2016
When multiple agents learn a task simultaneously in an environment, the learning results often become unstable. The problem is known as a concurrent learning problem and several methods have been proposed to resolve the problem so far. In this paper, we propose a new method that incorporates the expected failure probability (EFP) into the action selection strategy to give agents a kind of mutual adaptability. We confirm the effectiveness of the proposed method using Keepaway task.