| Presentation | 1998/7/27 Learning of an evaluation function of the game Othello by EM algorithm Taku Yoshioka, Shin Ishii, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this report, we discuss a learning method of Normalized Gaussian Network(NGnet)that evaluates states of the game Othello. In order to train the NGnet, we employ on-line EM algorithm, whose convergence was shown to be rapid in our previous studies. Consequently, the computer player employing the trained evaluation function becomes to beat a heuristic-based player with the winning rate of 73%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Othello / EM algorithm / Normalized Gaussian Network / Radial Basis Functions / Evaluation function / Reinforcement learning |
| Paper # | NC98-41 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1998/7/27(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 of an evaluation function of the game Othello by EM algorithm |
| Sub Title (in English) | |
| Keyword(1) | Othello |
| Keyword(2) | EM algorithm |
| Keyword(3) | Normalized Gaussian Network |
| Keyword(4) | Radial Basis Functions |
| Keyword(5) | Evaluation function |
| Keyword(6) | Reinforcement learning |
| 1st Author's Name | Taku Yoshioka |
| 1st Author's Affiliation | Nara Institute of Science and Technology() |
| 2nd Author's Name | Shin Ishii |
| 2nd Author's Affiliation | Nara Institute of Science and Technology |
| Date | 1998/7/27 |
| Paper # | NC98-41 |
| Volume (vol) | vol.98 |
| Number (no) | 219 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |