|
University of the Ryukyus Repository >
Faculty of Engineering >
Bulletin >
Bulletin of the Faculty of Engineering, University of the Ryukyus >
No. 54 (1997/09) >
| |
| Title | : | Q-learningを用いたマルチエージェントにおける協調行動獲得に関する研究 |
| Title alternative | : | Acquisition of Cooperative Behaviors Using with Q-learning in Multi-agent Environment |
| Authors | : | 玉城, 斉
遠藤, 聡志
山田, 孝治 |
| Authors alternative | : | Tamashiro, Tadashi
Endo, Satoshi
Yamada, Koji |
| Issue Date | : | Sep-1997 |
| Abstract | : | One of the important issues in intelligent systems and robotics is to develop an efficient method to control multi-agent system. In order to work the multi-agent system well as the problem solver, it's so significant to create cooperative behaviors among the agents. In the multi-agent system, the behaviors of cooperation emerged as the results of suitable role learning by each agent. In this paper, we design some fundamental computer experiments to investigate the emergence of cooperative behaviors in reinforcement learning based multi-agent system. We show that role learning for acquiring cooperative behaviors according to the result of these experiments. |
| Type Local | : | 紀要論文 |
| ISSN | : | 0389-102X |
| Publisher | : | 琉球大学工学部 |
| URI | : | http://hdl.handle.net/20.500.12000/14767 |
| Citation | : | 琉球大学工学部紀要 no.54 p.101 -108 |
| Appears in Collections | : | No. 54 (1997/09)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| No54p101.pdf | | 982Kb | Adobe PDF | View/Open |
|
|
|
