Presentation 2004/3/9
An Approach to Bargaining Problem Through Multi-Agent Reinforcement Learning
Akira ITO, Masafumi MIZUNO, Tatsuaki MATSUMOTO, Kazunori TERADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bargaining problem is how to find the contract point where the cooperation is preferable, but we must fight for the advantageous agreement. We approach bargaining problem from the multi agent learning standpoint. Each agent observes the opponent's behavior and tries to increase the expected interests by adjusting its own action appropriately. The cooperative solution is obtained through the pursuit of the self-interests of each agent. This method propose a new view for the meaning of the cooperative solution in bargaining problem.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) bargaining problem / multi agent / reinforcement learning / Q learning using history
Paper # AI2003-84
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) An Approach to Bargaining Problem Through Multi-Agent Reinforcement Learning
Sub Title (in English)
Keyword(1) bargaining problem
Keyword(2) multi agent
Keyword(3) reinforcement learning
Keyword(4) Q learning using history
1st Author's Name Akira ITO
1st Author's Affiliation Faculty of Engineering, Gifu University()
2nd Author's Name Masafumi MIZUNO
2nd Author's Affiliation Faculty of Engineering, Gifu University
3rd Author's Name Tatsuaki MATSUMOTO
3rd Author's Affiliation Faculty of Engineering, Gifu University
4th Author's Name Kazunori TERADA
4th Author's Affiliation Faculty of Engineering, Gifu University
Date 2004/3/9
Paper # AI2003-84
Volume (vol) vol.103
Number (no) 725
Page pp.pp.-
#Pages 6
Date of Issue