Presentation | 1997/7/24 Learning "stand-up" trajectories using reinforcement learning Jun Morimoto, Kenji Doya, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study we consideris the "stand-up" task for a two-joint, three-link robot. In contrast to the case of steady walking or standing, the optimal trajectory for such a transient behavior is very difficult to derive. The goal of the task is to find a path that links a lying state to an upright state. The geometry of the robot is such that there is no static solution; the robot has to stand up dynamically utilizing the momentum of its body. We use reinforcement learning, in particular, continuous time and state temporal difference (TD) learning method. Successful results were obtained by combining continuous TD with an efficient method of function approximation in high dimentional state space. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | reinfocement learning / motor control / robotics / stand up |
Paper # | NC97-28 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1997/7/24(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Learning "stand-up" trajectories using reinforcement learning |
Sub Title (in English) | |
Keyword(1) | reinfocement learning |
Keyword(2) | motor control |
Keyword(3) | robotics |
Keyword(4) | stand up |
1st Author's Name | Jun Morimoto |
1st Author's Affiliation | Graduate School of Infomation Science, Nara Institute of Science and Technology : ATR Human Information Processing Res. Labs.() |
2nd Author's Name | Kenji Doya |
2nd Author's Affiliation | Kawato Dynamic Brain Project, JST : Graduate School of Infomation Science, Nara Institute of Science and Technology |
Date | 1997/7/24 |
Paper # | NC97-28 |
Volume (vol) | vol.97 |
Number (no) | 201 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |