| Presentation | 2007-03-14 Prediction of the optimal parameter values in reinforcement learning based on interdependency Keiji KAMEI, Masumi ISHIKAWA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Reinfoecement learning is that we have to specify parameters values without prior information. We proposed to optimize the values of parameters in RL with the help of a genetic algorithm. The parameter values in RL depend on the environments. Since then, the method is impractical due to huge computational cost. In this paper, we propose to predict of the optimal parameter values in RL as a function of measures for the complexity of the environment, which are multiple regression analysis and Supervise SOM. As a result of expriments, we succeed in estimating the optimal parameter values in RL. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | reinforcement learning / genetic algorithm / mobile robot / optimal path / parameter dependency / parameter prediction |
| Paper # | NC2006-150 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2007/3/7(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) | Prediction of the optimal parameter values in reinforcement learning based on interdependency |
| Sub Title (in English) | |
| Keyword(1) | reinforcement learning |
| Keyword(2) | genetic algorithm |
| Keyword(3) | mobile robot |
| Keyword(4) | optimal path |
| Keyword(5) | parameter dependency |
| Keyword(6) | parameter prediction |
| 1st Author's Name | Keiji KAMEI |
| 1st Author's Affiliation | Dept. of Brain Science and Engineering Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology() |
| 2nd Author's Name | Masumi ISHIKAWA |
| 2nd Author's Affiliation | Dept. of Brain Science and Engineering Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology |
| Date | 2007-03-14 |
| Paper # | NC2006-150 |
| Volume (vol) | vol.106 |
| Number (no) | 588 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |