Presentation | 2001/3/16 A multi-agent reinforcement learning method with learning of other agents for competitive game Yoichiro Matsuno, Tatsuya Yaamazaki, Jun Matsuda, Shin Ishii, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This report proposes a reinforcement learning(RL)method based on the Actor-Critic architecture, which can be applied to partially-observable multi-agent competitive games. As an ezample, we consider a card game"Hearts". The RL then becomes a part,ally-observable Markov decision process (POMDP). In our method, a single Hearts game is divided into three stages, and three actors are prepared so that one of them plays and learns separately in each stage. In particular, the actor for the middle stage plays so as to enlarge the expected temporal-difference error, which is calculated using the evaluation function approximated by the critic and the estimated state transition. Computer experiments with heuristic players show that our RL method works well. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Multi-agent / Reinforcement learning / Competitive game / Actor-Critic model / Opponent-agent model inference |
Paper # | NC2000-168 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2001/3/16(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) | A multi-agent reinforcement learning method with learning of other agents for competitive game |
Sub Title (in English) | |
Keyword(1) | Multi-agent |
Keyword(2) | Reinforcement learning |
Keyword(3) | Competitive game |
Keyword(4) | Actor-Critic model |
Keyword(5) | Opponent-agent model inference |
1st Author's Name | Yoichiro Matsuno |
1st Author's Affiliation | Nara Institute of Science and Technology() |
2nd Author's Name | Tatsuya Yaamazaki |
2nd Author's Affiliation | ATR Adaptive Commuinications Research Laboratories |
3rd Author's Name | Jun Matsuda |
3rd Author's Affiliation | Osaka Gakuin Univercity |
4th Author's Name | Shin Ishii |
4th Author's Affiliation | Nara Institute of Science and Technology:CREST, Japan Science and Technology Corporation |
Date | 2001/3/16 |
Paper # | NC2000-168 |
Volume (vol) | vol.100 |
Number (no) | 688 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |