Encouragement of Right Social Norms by Inverse Reinforcement Learning

• Item type: JInfP(1)
• 公開日: 2014-04-15
• タイトル: Encouragement of Right Social Norms by Inverse Reinforcement Learning
• タイトル / 言語: en
• タイトル: Encouragement of Right Social Norms by Inverse Reinforcement Learning
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [Special Issue on Multiagent-based Societal Systems] inverse reinforcement learning, social norms
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Chiba University
• 著者所属: Japan Maritime Self-Defense Force
• 著者所属(英): en
• 著者所属(英): Chiba University
• 著者所属(英): en
• 著者所属(英): Japan Maritime Self-Defense Force
• 著者名: Sachiyo, Arai; Kanako, Suzuki
• 著者名(英): Sachiyo, Arai; Kanako, Suzuki
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This study is intended to encourage appropriate social norms among multiple agents. Effective norms, such as those emerging from sustained individual interactions over time, can make agents act cooperatively to optimize their performance. We introduce a “social learning” model in which agents mutually interact under a framework of the coordination game. Because coordination games have dual equilibria, social norms are necessary to make agents converge to a unique equilibrium. As described in this paper, we present the emergence of a right social norm by inverse reinforcement learning, which is an approach for extracting a reward function from the observation of optimal behaviors. First, we let a mediator agent estimate the reward function by inverse reinforcement learning from the observation of a master's behavior. Secondly, we introduce agents who act according to an estimated reward function in the multiagent world in which most agents, called citizens, have no way to act. Finally, we evaluate the effectiveness of introducing inverse reinforcement learning.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This study is intended to encourage appropriate social norms among multiple agents. Effective norms, such as those emerging from sustained individual interactions over time, can make agents act cooperatively to optimize their performance. We introduce a “social learning” model in which agents mutually interact under a framework of the coordination game. Because coordination games have dual equilibria, social norms are necessary to make agents converge to a unique equilibrium. As described in this paper, we present the emergence of a right social norm by inverse reinforcement learning, which is an approach for extracting a reward function from the observation of optimal behaviors. First, we let a mediator agent estimate the reward function by inverse reinforcement learning from the observation of a master's behavior. Secondly, we introduce agents who act according to an estimated reward function in the multiagent world in which most agents, called citizens, have no way to act. Finally, we evaluate the effectiveness of introducing inverse reinforcement learning.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA00700121
• 書誌情報: Journal of information processing; 巻 22, 号 2, p. 299-306, 発行日 2014-04-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-6652
• 出版者 / 言語: ja
• 出版者: 情報処理学会