The common idea is to consider agents whose mental state comprises the three attitudes of belief、desire andintention. The relationships among these entities have received considerable attention. There still remains a large gapbetween theory and practice. In this paper, the authors implement a BDI agent system based on rule reasoning andshow the procedure of planning. The experiment shows the system can handle application problem.
Reinforcement learning allows agent that has no knowledge of an environment to cooperate more efficacious each other. This paper presents an approach for developing multi-agent reinforcement learning systems based on equation principle. The experiment shows agent can produces the desired behavior under all kinds of situation.
