Presentation 1998/1/22
Evolutionary Learning of Payoff Configurations in Coalition for Cooperative Pursuit
Hideki SATO, Masayasu ATSUMI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In multi-agent environment, it is important to make a group of agents that solve each task rationally. The concept of coalition, which is proposed in the cooperative game theory, provides the rational criteria for making agents' group. We propose an evolutionary learning architecture based on the genetic programming that learns a rational coalition among agents and pursuit behavior under the coalition concurrently. In this paper, by using the extended pursuit problem as an example, we show that coalitions are formed and the effective pursuit behavior appears under the coalition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Coalition / Genetic Programming / game theory
Paper # AI97-64
Date of Issue

Conference Information
Committee AI
Conference Date 1998/1/22(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) Evolutionary Learning of Payoff Configurations in Coalition for Cooperative Pursuit
Sub Title (in English)
Keyword(1) Coalition
Keyword(2) Genetic Programming
Keyword(3) game theory
1st Author's Name Hideki SATO
1st Author's Affiliation Division of Info. Sys. Sci., Graduate school of Eng., Soka University()
2nd Author's Name Masayasu ATSUMI
2nd Author's Affiliation Division of Info. Sys. Sci., Graduate school of Eng., Soka University
Date 1998/1/22
Paper # AI97-64
Volume (vol) vol.97
Number (no) 498
Page pp.pp.-
#Pages 8
Date of Issue