| Presentation | 1996/5/24 Emergent Organization of Coordinated Behavior by Modular Reinforcement-Learning Agents Kenji FUKUMOTO, Osamu IKEDA, Norihiko ONO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently several attempts have been reported to let multiple monolithic reinforcement-learning agents synthesize coordinated decision policies needed to accomplish their common goals effectively. Most of these straightforward reinforcement-learning approaches, however, scale poorly to more complex multi-agent learning problems, because the state space for each learning agent grows exponentially in the number of its partner agents engaged in the joint task. In this paper, taking the Pursuit Problem as such a learning problem that is computationally intractable by these straightforward approaches, we show how successfully a collection of modular Q-learning pursuer agents synthesize coordinated decision policies needed to capture a randomly-fleeing fugitive agent effectively, by specializing their individual functionality and organizing herding behavior. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | multi-agent systems / machine learning / reinforcement-learning |
| Paper # | AI96-5 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 1996/5/24(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) | Emergent Organization of Coordinated Behavior by Modular Reinforcement-Learning Agents |
| Sub Title (in English) | |
| Keyword(1) | multi-agent systems |
| Keyword(2) | machine learning |
| Keyword(3) | reinforcement-learning |
| 1st Author's Name | Kenji FUKUMOTO |
| 1st Author's Affiliation | Faculty of Engineering, University of Tokushima() |
| 2nd Author's Name | Osamu IKEDA |
| 2nd Author's Affiliation | Faculty of Engineering, University of Tokushima |
| 3rd Author's Name | Norihiko ONO |
| 3rd Author's Affiliation | Faculty of Engineering, University of Tokushima |
| Date | 1996/5/24 |
| Paper # | AI96-5 |
| Volume (vol) | vol.96 |
| Number (no) | 77 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |