| Presentation | 2003/7/22 An Adaptive Strategy Model for Opponent's Characteristics based on Reinforcement Learning Masahiro Ono, Mitsuru Shiozaki, Mamoru Sasaki, Atsushi Iwata, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In order to create a robot brain having intelligent action strategies, we proposed a model for making strategy for winning a game. During a game, It can make several strategies, and adaptively select/switch them to opponent feature change. For strategy making algorithm, Q-PSP reinforced learning are used because of faster learning speed. Selection and sweitching of the formed strategies are done based on the similarity between two kinds of Q-functions : (1) Q_x is obtained at each strategy learning, and (2) Q_m is used to recognize features of an opponent. We made a simulation Program for an air hockey game based on the proposed strategy model. As results of simulation, we confirmed the operations of strategy making and selection/switching, and evaluate the effectiveness of the proposed model. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | brain of robot / strategy model / reinforcement learning / Q-function / strategy making / strategy selecting-switching |
| Paper # | NC2003-44 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2003/7/22(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) | An Adaptive Strategy Model for Opponent's Characteristics based on Reinforcement Learning |
| Sub Title (in English) | |
| Keyword(1) | brain of robot |
| Keyword(2) | strategy model |
| Keyword(3) | reinforcement learning |
| Keyword(4) | Q-function |
| Keyword(5) | strategy making |
| Keyword(6) | strategy selecting-switching |
| 1st Author's Name | Masahiro Ono |
| 1st Author's Affiliation | Graduate School of Advance Sciences of Matter, Hiroshima University() |
| 2nd Author's Name | Mitsuru Shiozaki |
| 2nd Author's Affiliation | Graduate School of Advance Sciences of Matter, Hiroshima University |
| 3rd Author's Name | Mamoru Sasaki |
| 3rd Author's Affiliation | Graduate School of Advance Sciences of Matter, Hiroshima University |
| 4th Author's Name | Atsushi Iwata |
| 4th Author's Affiliation | Graduate School of Advance Sciences of Matter, Hiroshima University |
| Date | 2003/7/22 |
| Paper # | NC2003-44 |
| Volume (vol) | vol.103 |
| Number (no) | 228 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |