An Intrinsically Motivated Robot Explores Non-reward Environments with Output Arbitration

Takuma Seno, Masahiko Osawa, Michita Imai

研究成果: Conference contribution

抄録

In real worlds, rewards are easily sparse because the state space is huge. Reinforcement learning agents have to achieve exploration skills to get rewards in such an environment. In that case, curiosity defined as internally generated rewards for state prediction error can encourage agents to explore environments. However, when a robot learns its policy by reinforcement learning, changing outputs of the policy cause jerking because of inertia. Jerking prevents state prediction from convergence, which would make the policy learning unstable. In this paper, we propose Arbitrable Intrinsically Motivated Exploration (AIME), which enables robots to stably learn curiosity-based exploration. AIME uses Accumulator Based Arbitration Model (ABAM) that we previously proposed as an ensemble learning method inspired by prefrontal cortex. ABAM adjusts motor controls to improve stability of reward generation and reinforcement learning. In experiments, we show that a robot can explore a non-reward simulated environment with AIME.

本文言語English
ホスト出版物のタイトルBiologically Inspired Cognitive Architectures 2018 - Proceedings of the Ninth Annual Meeting of the BICA Society
編集者Alexei V. Samsonovich
出版社Springer Verlag
ページ283-289
ページ数7
ISBN(印刷版)9783319993157
DOI
出版ステータスPublished - 2019
イベント9th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2018 - Prague, Czech Republic
継続期間: 2018 8月 222018 8月 24

出版物シリーズ

名前Advances in Intelligent Systems and Computing
848
ISSN(印刷版)2194-5357

Other

Other9th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2018
国/地域Czech Republic
CityPrague
Period18/8/2218/8/24

ASJC Scopus subject areas

  • 制御およびシステム工学
  • コンピュータ サイエンス(全般)

フィンガープリント

「An Intrinsically Motivated Robot Explores Non-reward Environments with Output Arbitration」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル