Abstract
Recently, application of a multi agent system is expected from the viewpoint of the parallel and distributed processing of systems. Reinforcement learning attracts attention as an implementing method of the multi agent systems. However, there is a problem that the more the number of agents to deal with increases, the slower the speed of learning becomes. To solve this problem, we propose a new reinforcement learning that can learn quickly and reduce the amount of memory. It tries to increase efficiency of the learning on a tracking problem by using a method paying attention to partial states of two agents among a large number of agents.
