ロボティクス・メカトロニクス講演会講演概要集
Online ISSN : 2424-3124
セッションID: 2P1-G12
会議情報
2P1-G12 並列処理を用いた価値関数合成による強化学習の効率化
仲間 祐貴當眞 嗣久山田 孝治遠藤 聡志
著者情報
会議録・要旨集 フリー

詳細
抄録
In this paper, efficiency improvement of reinforcement learning using parallel processing for combination value function. We propose the method of periodically composing Q table of local learning clusters to global Q table. We apply this method to two applications. One is maze problem and an another is behavior rule detection problem for modular typed robot. Q Learning method and Monte Carlo method are compared with profit share method that learns robot behaviors. We presented computer experiments of 40 PC clusters. The convergence time and learning times are evaluated and discussed.
著者関連情報
© 2010 一般社団法人 日本機械学会
前の記事 次の記事
feedback
Top