| Presentation | 2007-12-22 A Modification Algorithm of Function Approximator for the Reinforcement Learning with Reusing Mechanism of Avoidance Actions : Proposal and its Application to Motion Learning of Multi-Link Robot Akihiko YAMAGUCHI, Norikazu SUGIMOTO, Mitsuo KAWATO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Applying a learning method, such as reinforcement learning, to learning motions of multi-link robots requires large cost, such as damage from falling down. To overcome this problem, we proposed a reusing mechanism for reinforcement learning where the avoidance actions, such as not to fall down, are learned separately from primary actions, then they are reused in learning new tasks [1]. A method to apply it to learning whole-body motions of 4-link robot whose base is not fixed to a ground was also developed. In this paper, we propose a new method to modify basis functions of a function approximator of an action value function to improve the separative performance, and demonstrate the method works effectively in learning whole-body motions of a multi-link robot. Furthermore, we investigate a learning cost of damage from falling down in learning whole-body motions is reduced by reusing avoidance actions. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | motion learning / reinforcement learning / reusing / avoidance actions / jumpping / serve |
| Paper # | NC2007-86 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2007/12/15(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) | A Modification Algorithm of Function Approximator for the Reinforcement Learning with Reusing Mechanism of Avoidance Actions : Proposal and its Application to Motion Learning of Multi-Link Robot |
| Sub Title (in English) | |
| Keyword(1) | motion learning |
| Keyword(2) | reinforcement learning |
| Keyword(3) | reusing |
| Keyword(4) | avoidance actions |
| Keyword(5) | jumpping |
| Keyword(6) | serve |
| 1st Author's Name | Akihiko YAMAGUCHI |
| 1st Author's Affiliation | Nara Institute of Science and Technology:ATR Computational Neuroscience Laboratories() |
| 2nd Author's Name | Norikazu SUGIMOTO |
| 2nd Author's Affiliation | ATR Computational Neuroscience Laboratories |
| 3rd Author's Name | Mitsuo KAWATO |
| 3rd Author's Affiliation | ATR Computational Neuroscience Laboratories:Nara Institute of Science and Technology |
| Date | 2007-12-22 |
| Paper # | NC2007-86 |
| Volume (vol) | vol.107 |
| Number (no) | 410 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |