Presentation | 2005/3/22 Examination of Q-learning and detailed correction of the action policy of robot in real environment Yuu TAKAI, Hiroki SUYARI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | When a robot learns some action policies on real time for given environments, a large memory capacity and time are required. In order to reduce the required memory and time for given environments, we present a method of improving an action policy obtained in Q-learning. In other words, our method enables an action policy obtained in one environment to apply to other environment with small modification. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Reinforcement Learning / Q-learning |
Paper # | NC2004-184 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2005/3/22(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) | Examination of Q-learning and detailed correction of the action policy of robot in real environment |
Sub Title (in English) | |
Keyword(1) | Reinforcement Learning |
Keyword(2) | Q-learning |
1st Author's Name | Yuu TAKAI |
1st Author's Affiliation | Graduate School of Science and Technology, Chiba University() |
2nd Author's Name | Hiroki SUYARI |
2nd Author's Affiliation | Department of Information and Image Science, Chiba University |
Date | 2005/3/22 |
Paper # | NC2004-184 |
Volume (vol) | vol.104 |
Number (no) | 759 |
Page | pp.pp.- |
#Pages | 5 |
Date of Issue |