An analysis of U-Mart experiments by machine and human agents
暂无分享,去创建一个
One of the most distinguishing features of the U-Mart system is that both the human trader agents and computer program machine agents can participate in the market simultaneously. The purpose of this paper is to analyze results of U-Mart experiments by both human and machine agents. Regarding machine agent experiments, more than 40 agents who belonged to 12 different teams participated. A series of experiments were conducted with 28 human agents, who were the third year students of the university, and 20 machine agents together for human agent experiments. U-Mart system can be also used as an educational courseware program for students who learn economics and engineering. This paper also reports what they could learn and could not learn by a series of experiments.
[1] Isao Ono,et al. Constructing Approximation Models Based on Agent-Based Simulations by Genetic Algorithms , 2001 .
[2] Hiroshi Sato,et al. U-Mart: A Test Bed for Interdisciplinary Research into Agent-Based Artificial Markets , 2001 .
[3] Hajime Kita,et al. U-Mart: An Artificial Market Testbed for Economics and Multiagent Systems , 2003 .
[4] Isao Ono,et al. U-Mart Project: Learning Economic Principles from the Bottom by Both Human and Software Agents , 2001, JSAI Workshops.