RESEARCH ON MULTI-AGENT-BASED SIMULATION OF SUPERVISION ISSUES
Supervision issues exist among almost every industry of this world. Based on a multi-agent modeling and simulation approach, this paper, which is different from the existing researches, designs the interaction rules of supervision and violation, builds the evolving mechanism using genetic algorithm, and simulates the evolving process on the swarm platform. On the basis of the results of the simulation, it reach the conclusion that under the condition of bounded rationality and incomplete information, to eliminate the violation, the supervisor must obtain almost the complete information of the behavior of actors, apart from making their expected revenue of obedience greater than the expected revenue of violation. A heavier punishment can accelerate the progress of the evolution.
Supervision Multi-agent Complezity Genetic Algorithm Swarm
CHANG-HONG LI TIE LI
School of Management, Shanxi University, Taiyuan 030006, China
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
2347-2351
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）