TY - GEN
T1 - “Re:ROS”
T2 - 1st International Early Research Career Enhancement School on Biologically Inspired Cognitive Architectures, FIERCES on BICA 2017
AU - Ueno, Sei
AU - Osawa, Masahiko
AU - Imai, Michita
AU - Kato, Tsuneo
AU - Yamakawa, Hiroshi
N1 - Publisher Copyright:
© Springer International Publishing AG 2018.
PY - 2018
Y1 - 2018
N2 - 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.”.
AB - 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.”.
KW - Cognitive architecture
KW - Reinforcement learning
KW - Reinforcement learning environment
KW - Robotics
UR - http://www.scopus.com/inward/record.url?scp=85059147983&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059147983&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-63940-6_28
DO - 10.1007/978-3-319-63940-6_28
M3 - Conference contribution
AN - SCOPUS:85059147983
SN - 9783319639390
T3 - Advances in Intelligent Systems and Computing
SP - 198
EP - 203
BT - Biologically Inspired Cognitive Architectures (BICA) for Young Scientists - Proceedings of the 1st International Early Research Career Enhancement School on BICA and Cybersecurity, FIERCES 2017
A2 - Samsonovich, Alexei V.
A2 - Samsonovich, Alexei V.
A2 - Klimov, Valentin V.
PB - Springer
Y2 - 1 August 2017 through 6 August 2017
ER -