Presentation | 2004/3/9 Multi-Agent Reinforcement Learning with the Partly High-dimensional State Space Kazuyuki FUJITA, Hiroshi MATSUO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In Multi-Agent Reinforcement Learning, each agent observe a state of other agents as a part of environment. Therefore, the state space is exponential in the number of agents and learning speed significantly decrease. Modular Q-learning [6] needs very small state space. However, the incomplete observation involves a decline in the performance. In this paper, we improve Modular Q-learning's performance with the partly high-dimensional state space. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Multi Agent / Reinforcement Learning / Modular Q-learning / State Space |
Paper # | AI2003-92 |
Date of Issue |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2004/3/9(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 | Artificial Intelligence and Knowledge-Based Processing (AI) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Multi-Agent Reinforcement Learning with the Partly High-dimensional State Space |
Sub Title (in English) | |
Keyword(1) | Multi Agent |
Keyword(2) | Reinforcement Learning |
Keyword(3) | Modular Q-learning |
Keyword(4) | State Space |
1st Author's Name | Kazuyuki FUJITA |
1st Author's Affiliation | Department of Computer Engineering, Nagoya Institute of Technology() |
2nd Author's Name | Hiroshi MATSUO |
2nd Author's Affiliation | Department of Computer Engineering, Nagoya Institute of Technology |
Date | 2004/3/9 |
Paper # | AI2003-92 |
Volume (vol) | vol.103 |
Number (no) | 725 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |