Analysis of learning types in an artificial market

Authors:
Kiyoshi Izumi;Tomohisa Yamashita;Koichi Kurumatani
Affiliations:
ITRI, AIST & CREST, JST, Tokyo, Japan;ITRI, AIST & CREST, JST, Tokyo, Japan;ITRI, AIST & CREST, JST, Tokyo, Japan
Venue:
MABS'04 Proceedings of the 2004 international conference on Multi-Agent and Multi-Agent-Based Simulation
Year:
2004

Citing 4
Cited 2

Complexity of Agents and Complexity of Markets

Proceedings of the Joint JSAI 2001 Workshop on New Frontiers in Artificial Intelligence
Development of an artificial market model based on a field study

Information Sciences: an International Journal - Special issue: Computational intelligence in economics and finance
Agent-based computational modeling of the stock price-volume relation

Information Sciences: an International Journal - Special issue: Computational intelligence in economics and finance
Phase transition in a foreign exchange market-analysis based on anartificial market approach

IEEE Transactions on Evolutionary Computation

Adaptive manager-side control policy in contract net protocol for massively multi-agent systems

Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 3
Controling Contract Net Protocol by Local Observation for Large-Scale Multi-Agent Systems

CIA '08 Proceedings of the 12th international workshop on Cooperative Information Agents XII

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we examined the conditions under which evolutionary algorithms (EAs) are appropriate for artificial market models. We constructed three types of agents, which are different in efficiency and accuracy of learning. They were compared using acquired payoff in a minority game, a simplified model of a financial market. As a result, when the dynamics of the financial price was complex to some degree, an EA-like learning type was appropriate for the modeling of financial markets.