“Re:ROS”: Prototyping of Reinforcement Learning Environment for Asynchronous Cognitive Architecture

Sei Ueno, Masahiko Osawa, Michita Imai, Tsuneo Kato, Hiroshi Yamakawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Reinforcement learning (RL), which is a field of machine learning, is effective for behavior acquisition in robots. Asynchronous cognitive architecture, which is a method to model human intelligence, is also effective for behavior acquisition. Accordingly, the combination of RL and asynchronous cognitive architecture is expected to be effective. However, early work on the RL toolkit cannot apply asynchronous cognitive architecture because it cannot solve the difference between the asynchrony, which the asynchronous cognitive architecture has, and the synchrony, which RL modules have. In this study, we propose an RL environment for robots that can apply the asynchronous cognitive architecture by applying asynchronous systems to RL modules. We prototyped the RL environment named “Re:ROS.”.

Original languageEnglish
Title of host publicationBiologically Inspired Cognitive Architectures (BICA) for Young Scientists - Proceedings of the 1st International Early Research Career Enhancement School on BICA and Cybersecurity, FIERCES 2017
EditorsAlexei V. Samsonovich, Alexei V. Samsonovich, Valentin V. Klimov
PublisherSpringer
Pages198-203
Number of pages6
ISBN (Print)9783319639390
DOIs
Publication statusPublished - 2018
Event1st International Early Research Career Enhancement School on Biologically Inspired Cognitive Architectures, FIERCES on BICA 2017 - Moscow, Russian Federation
Duration: 2017 Aug 12017 Aug 6

Publication series

NameAdvances in Intelligent Systems and Computing
Volume636
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference1st International Early Research Career Enhancement School on Biologically Inspired Cognitive Architectures, FIERCES on BICA 2017
CountryRussian Federation
CityMoscow
Period17/8/117/8/6

Keywords

  • Cognitive architecture
  • Reinforcement learning
  • Reinforcement learning environment
  • Robotics

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of '“Re:ROS”: Prototyping of Reinforcement Learning Environment for Asynchronous Cognitive Architecture'. Together they form a unique fingerprint.

  • Cite this

    Ueno, S., Osawa, M., Imai, M., Kato, T., & Yamakawa, H. (2018). “Re:ROS”: Prototyping of Reinforcement Learning Environment for Asynchronous Cognitive Architecture. In A. V. Samsonovich, A. V. Samsonovich, & V. V. Klimov (Eds.), Biologically Inspired Cognitive Architectures (BICA) for Young Scientists - Proceedings of the 1st International Early Research Career Enhancement School on BICA and Cybersecurity, FIERCES 2017 (pp. 198-203). (Advances in Intelligent Systems and Computing; Vol. 636). Springer. https://doi.org/10.1007/978-3-319-63940-6_28