Controllability of population characteristics of IPD game players based on the spatial structure

Masahiro Ono, Mitsuru Ishizuka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we deal with the influence of the spatial structure, which limits the communication of agents, on the characteristics of individual agents. We investigate the population characteristics and the behavior of the agents playing iterated prisoner's dilemma (IPD) games on the spatial structure. We first propose a new agent model that plays the IPD game, which contains the gene of the coded parameters of reinforcement learning. The agents evolve and learn while playing the games. Second, we report an empirical study. In our simulation, we observe that the spatial structure affects learning and evolution. Learning is generally not conducive to the mutual cooperation between agents, except in some special conditions. Then, we try to control the population characteristics. We find that they are controllable to some extent when we fix the strategies of several agents.

Original languageEnglish
Title of host publicationAAAI Fall Symposium - Technical Report
Pages119-126
Number of pages8
VolumeFS-06-05
Publication statusPublished - 2006
Externally publishedYes
Event2006 AAAI Fall Symposium - Arlington, VA
Duration: 2006 Oct 132006 Oct 15

Other

Other2006 AAAI Fall Symposium
CityArlington, VA
Period06/10/1306/10/15

Fingerprint

Controllability
Reinforcement learning
Genes
Communication

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ono, M., & Ishizuka, M. (2006). Controllability of population characteristics of IPD game players based on the spatial structure. In AAAI Fall Symposium - Technical Report (Vol. FS-06-05, pp. 119-126)

Controllability of population characteristics of IPD game players based on the spatial structure. / Ono, Masahiro; Ishizuka, Mitsuru.

AAAI Fall Symposium - Technical Report. Vol. FS-06-05 2006. p. 119-126.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ono, M & Ishizuka, M 2006, Controllability of population characteristics of IPD game players based on the spatial structure. in AAAI Fall Symposium - Technical Report. vol. FS-06-05, pp. 119-126, 2006 AAAI Fall Symposium, Arlington, VA, 06/10/13.
Ono M, Ishizuka M. Controllability of population characteristics of IPD game players based on the spatial structure. In AAAI Fall Symposium - Technical Report. Vol. FS-06-05. 2006. p. 119-126
Ono, Masahiro ; Ishizuka, Mitsuru. / Controllability of population characteristics of IPD game players based on the spatial structure. AAAI Fall Symposium - Technical Report. Vol. FS-06-05 2006. pp. 119-126
@inproceedings{ab9bbfe6698945c3b37cdc02550856cb,
title = "Controllability of population characteristics of IPD game players based on the spatial structure",
abstract = "In this paper, we deal with the influence of the spatial structure, which limits the communication of agents, on the characteristics of individual agents. We investigate the population characteristics and the behavior of the agents playing iterated prisoner's dilemma (IPD) games on the spatial structure. We first propose a new agent model that plays the IPD game, which contains the gene of the coded parameters of reinforcement learning. The agents evolve and learn while playing the games. Second, we report an empirical study. In our simulation, we observe that the spatial structure affects learning and evolution. Learning is generally not conducive to the mutual cooperation between agents, except in some special conditions. Then, we try to control the population characteristics. We find that they are controllable to some extent when we fix the strategies of several agents.",
author = "Masahiro Ono and Mitsuru Ishizuka",
year = "2006",
language = "English",
isbn = "157735303X",
volume = "FS-06-05",
pages = "119--126",
booktitle = "AAAI Fall Symposium - Technical Report",

}

TY - GEN

T1 - Controllability of population characteristics of IPD game players based on the spatial structure

AU - Ono, Masahiro

AU - Ishizuka, Mitsuru

PY - 2006

Y1 - 2006

N2 - In this paper, we deal with the influence of the spatial structure, which limits the communication of agents, on the characteristics of individual agents. We investigate the population characteristics and the behavior of the agents playing iterated prisoner's dilemma (IPD) games on the spatial structure. We first propose a new agent model that plays the IPD game, which contains the gene of the coded parameters of reinforcement learning. The agents evolve and learn while playing the games. Second, we report an empirical study. In our simulation, we observe that the spatial structure affects learning and evolution. Learning is generally not conducive to the mutual cooperation between agents, except in some special conditions. Then, we try to control the population characteristics. We find that they are controllable to some extent when we fix the strategies of several agents.

AB - In this paper, we deal with the influence of the spatial structure, which limits the communication of agents, on the characteristics of individual agents. We investigate the population characteristics and the behavior of the agents playing iterated prisoner's dilemma (IPD) games on the spatial structure. We first propose a new agent model that plays the IPD game, which contains the gene of the coded parameters of reinforcement learning. The agents evolve and learn while playing the games. Second, we report an empirical study. In our simulation, we observe that the spatial structure affects learning and evolution. Learning is generally not conducive to the mutual cooperation between agents, except in some special conditions. Then, we try to control the population characteristics. We find that they are controllable to some extent when we fix the strategies of several agents.

UR - http://www.scopus.com/inward/record.url?scp=33947280522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947280522&partnerID=8YFLogxK

M3 - Conference contribution

SN - 157735303X

SN - 9781577353034

VL - FS-06-05

SP - 119

EP - 126

BT - AAAI Fall Symposium - Technical Report

ER -