Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4962250 | Procedia Computer Science | 2016 | 8 Pages |
Abstract
In a multi-agent learning where multiple agents are learning, there is a problem about an indirect reward that is how to distribute a reward to an agent that does not obtain a reward directly. We have shown the theorem [3] about “negative effect” of an indirect reward. This paper focuses on the “positive effect” of an indirect reward such as an elimination of the perceptual aliasing problem [1]. First, we describe the relationship the theorem [3] and the “positive effect” of the indirect reward. Next, we propose a method to eliminate the perceptual aliasing problem and show the effectiveness of the proposed method by numerical examples.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science (General)
Authors
Kazuteru Miyazaki,