Presentation 1995/11/16
Emergent Organization of Communication, Specialization, and Herding-Behavior among Reinforcement-Learning Agents
Norihiko Ono,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To investigate the learning capabilities of reinforcement-learning agents under multi-agent environments, we have attempted to let multiple reinforcement-learning agents synthesize coordinated decision policies needed to accomplish their common goals effectively. So long as a small number of agents are engaged in their joint tasks and accordingly the state space for each agent is relatively small, even monolithic reinforcement-learning agents have successfully organized some interesting coordinated behavior. Most of such 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. This paper presents a modular reinforcement-learning approach to this kind of multi-agent learning problems and demonstrates its effective learning capabilities.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multi-agent systems / machine learning / reinforcement-learning
Paper # AI95-39,PRU95-154
Date of Issue

Conference Information
Committee AI
Conference Date 1995/11/16(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 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 Communication, Specialization, and Herding-Behavior among Reinforcement-Learning Agents
Sub Title (in English)
Keyword(1) multi-agent systems
Keyword(2) machine learning
Keyword(3) reinforcement-learning
1st Author's Name Norihiko Ono
1st Author's Affiliation Faculty of Engineering, University of Tokushima()
Date 1995/11/16
Paper # AI95-39,PRU95-154
Volume (vol) vol.95
Number (no) 363
Page pp.pp.-
#Pages 8
Date of Issue