Summary

International Symposium on Nonlinear Theory and its Applications

2009

Session Number:A2L-D

Session:

Number:A2L-D3

Reinforcement Learning using Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution

Yuko OSANA,  

pp.-

Publication Date:2009/10/18

Online ISSN:2188-5079

DOI:10.34385/proc.43.A2L-D3

PDF download (387.5KB)

Summary:
In this paper, we propose a reinforcement learning method using Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution (KFMPAM-WD). The proposed method is based on the actor-critic method, and the actor is realized by the KFMPAM-WD. The KFMPAM-WD is based on the self-organizing feature map, and it can realize successive learning and one-to-many associations. The proposed method makes use of this property in order to realize the learning during the practice of task. We carried out a series of computer experiments, and confirmed the effectiveness of the proposed method in path-finding problem.