Presentation | 2023-01-29 Continuous Value Control of Robot with Reservoir Actor-Critic Model Koutaro Minato, Yuichi Katori, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Deep learning is expected to be utilized to control robots operating in complex environments, but this requires a large amount of data, training time, and power. Robot control using reservoir computing (RC) has been proposed as a method to solve this problem, but the control method when the control signal is a continuous value has yet to be elucidated. In this study, the actor-critic method, one of the reinforcement learning methods, is combined with RC to construct a model of robot control that requires control by continuous values. We report that the reservoir actor-critic model performs well in a car mountain climbing task (MountainCarContinuous-v0), which requires continuous-valued control. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | reservoir computing / reinforcement learning / actor-critic method / continuous action space |
Paper # | NLP2022-103,NC2022-87 |
Date of Issue | 2023-01-21 (NLP, NC) |
Conference Information | |
Committee | NC / NLP |
---|---|
Conference Date | 2023/1/28(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Future University Hakodate |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | NC, NLP, etc. |
Chair | Hiroshi Yamakawa(Univ of Tokyo) / Akio Tsuneda(Kumamoto Univ.) |
Vice Chair | Hirokazu Tanaka(Tokyo City Univ.) / Hiroyuki Torikai(Hosei Univ.) |
Secretary | Hirokazu Tanaka(NTT) / Hiroyuki Torikai(NICT) |
Assistant | Yoshimasa Tawatsuji(Waseda Univ.) / Tomoki Kurikawa(KMU) / Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on Nonlinear Problems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Continuous Value Control of Robot with Reservoir Actor-Critic Model |
Sub Title (in English) | |
Keyword(1) | reservoir computing |
Keyword(2) | reinforcement learning |
Keyword(3) | actor-critic method |
Keyword(4) | continuous action space |
1st Author's Name | Koutaro Minato |
1st Author's Affiliation | Future University Hakodate(Future Univ Hakodate) |
2nd Author's Name | Yuichi Katori |
2nd Author's Affiliation | Future University Hakodate(Future Univ Hakodate) |
Date | 2023-01-29 |
Paper # | NLP2022-103,NC2022-87 |
Volume (vol) | vol.122 |
Number (no) | NLP-373,NC-374 |
Page | pp.pp.118-122(NLP), pp.118-122(NC), |
#Pages | 5 |
Date of Issue | 2023-01-21 (NLP, NC) |