Inverse Reinforcement Learning for Behavior Simulation with Contextual Actions and Multiple Policies

• Item type: SIG Technical Reports(1)
• 公開日: 2019-03-02
• タイトル: Inverse Reinforcement Learning for Behavior Simulation with Contextual Actions and Multiple Policies
• タイトル / 言語: en
• タイトル: Inverse Reinforcement Learning for Behavior Simulation with Contextual Actions and Multiple Policies
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: National Institute of Advanced Industrial Science and Technology
• 著者所属: National Institute of Advanced Industrial Science and Technology
• 著者所属(英): en
• 著者所属(英): National Institute of Advanced Industrial Science and Technology
• 著者所属(英): en
• 著者所属(英): National Institute of Advanced Industrial Science and Technology
• 著者名: Nahum, Alvarez; Itsuki, Noda
• 著者名(英): Nahum, Alvarez; Itsuki, Noda
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Machine learning is a discipline with many simulator-driven applications oriented to learn behavior. However, behavior simulation it comes with a number of associated difficulties, like the lack of a clear reward function, actions that depend of the state of the actor and the alternation of different policies. We present a method for behavior learning called Contextual Action Multiple Policy Inverse Reinforcement Learning (CAMP-IRL) that tackles those factors. Our method allows to extract multiple reward functions and generates different behavior profiles from them. We applied our method to a large scale crowd simulator using intelligent agents to imitate pedestrian behavior, making the virtual pedestrians able to switch between behaviors depending of the goal they have and navigating efficiently across unknown environments.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Machine learning is a discipline with many simulator-driven applications oriented to learn behavior. However, behavior simulation it comes with a number of associated difficulties, like the lack of a clear reward function, actions that depend of the state of the actor and the alternation of different policies. We present a method for behavior learning called Contextual Action Multiple Policy Inverse Reinforcement Learning (CAMP-IRL) that tackles those factors. Our method allows to extract multiple reward functions and generates different behavior profiles from them. We applied our method to a large scale crowd simulator using intelligent agents to imitate pedestrian behavior, making the virtual pedestrians able to switch between behaviors depending of the goal they have and navigating efficiently across unknown environments.
• 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: AA11135936
• 書誌情報: 研究報告知能システム（ICS）; 巻 2019-ICS-194, 号 6, p. 1-8, 発行日 2019-03-02
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-885X
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会