目的制限に基づく通信なしマルチエージェント協調行動学習とその効果の証明

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2020/01/01

タイトル(英語): Theoretical Learning Goal Selection for Non-Communicative Multi-Agent Cooperation

著者名: 上野　史（電気通信大学），髙玉　圭樹（電気通信大学）

著者名(英語): Fumito Uwano (The University of Electro-Communications), Keiki Takadama (The University of Electro-Communications)

キーワード: 強化学習，マルチエージェントシステム，報酬設計　　reinforcement learning，multi-agent system，reward management

要約(英語): This paper extended PMRL as the non-communicative and theoretical method for two agents, and proposed PLA as the method to be able to force agents to learn cooperative behavior for any number of agents. In addition, this paper adds the theoretic explanation for PLA that all agents achieve all purposes without spending the largest times. Concretely PLA forces each agent to avoid the more difficult purposes requiring many time to be reached by limiting the purpose which it can achieve, and it forces the agents to learn cooperative policy as achieving the appropriate purpose among the limited purposes. The experimental results in this paper derive that (1) PLA enables the agents to learn cooperative policy in the two grid world problems for three and five agents, and (2) PLA can force all agents to achieve all purposes in the problems with the minimum time.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.140 No.1 （2020） 特集：電子回路関連技術

本誌掲載ページ: 75-84 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/140/1/140_75/_article/-char/ja/