Presentation 2000/5/18
Multi-agent reinforcement learning methods using the estimation of the other agent's internal model
Nagayasu Yasuo, Ishii Shin,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The application of reinforcement learning to multi-agent systems has attracted recent attention. In a multi-agent environment, whether one agent's action is good or not depends on the other agents. We formerly proposed a multi-agent reinforcement learning method based on the estimation of the other agent's internal model. There, the internal model was estimated by the observation of past actions of the other agent. In this study, we consider a self-reference method for estimating the other agent's internal model. By using the pursuit problem as a testbed, we compare the two estimation methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multi-agent reinforcement learning / Q-learning / internal model / pursuit problem / self-reference
Paper # AI2000-4
Date of Issue

Conference Information
Committee AI
Conference Date 2000/5/18(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 methods using the estimation of the other agent's internal model
Sub Title (in English)
Keyword(1) multi-agent reinforcement learning
Keyword(2) Q-learning
Keyword(3) internal model
Keyword(4) pursuit problem
Keyword(5) self-reference
1st Author's Name Nagayasu Yasuo
1st Author's Affiliation Nara Institute of Science and Technology()
2nd Author's Name Ishii Shin
2nd Author's Affiliation Nara Institute of Science and Technology
Date 2000/5/18
Paper # AI2000-4
Volume (vol) vol.100
Number (no) 88
Page pp.pp.-
#Pages 8
Date of Issue