| Presentation | 2008-03-28 A Multi-agent Reinforcement Learning with Parallel Computation and its Application to Chaos Control Norihisa SATO, Masaharu ADACHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A reinforcement learning is a trial and error process, therefore it takes a huge computation time. It multiple agents can learn simultaneously the computational time can be reduced. In this paper we attempt to apply a multi-agent reinforcement learning to chaos control. We implement a multi-agent reinforcement learning using Message-Passing Interface. We compared the control performance of the multi-agent reinforcement learning and that of a single agent reinforcement learning. As a result, the multi-agent reinforcement learning show almost the same performance with the single-agent one. Even if learning iterate for a many times. Moreover, it is suggested that the quantized states whose action after learning by the multi-agent are the same, are important locations for the chaos control. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | control of chaos / reinforcement lerning / MPI (Message-Passing Interface) |
| Paper # | NLP2007-169 |
| Date of Issue |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2008/3/21(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 | Nonlinear Problems (NLP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Multi-agent Reinforcement Learning with Parallel Computation and its Application to Chaos Control |
| Sub Title (in English) | |
| Keyword(1) | control of chaos |
| Keyword(2) | reinforcement lerning |
| Keyword(3) | MPI (Message-Passing Interface) |
| 1st Author's Name | Norihisa SATO |
| 1st Author's Affiliation | School of Engineering, Tokyo Denki University() |
| 2nd Author's Name | Masaharu ADACHI |
| 2nd Author's Affiliation | School of Engineering, Tokyo Denki University |
| Date | 2008-03-28 |
| Paper # | NLP2007-169 |
| Volume (vol) | vol.107 |
| Number (no) | 561 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |