Abstract
In this paper, Rationally oriented Forgettable Profit Sharing method (RFPS) for reinforcement learning is proposed. Although the Profit Sharing (PS) provides good performances in real environments, its learning is often slow in long term tasks because it is difficult to determine the adequate discount rate which satisfies the Miyazaki rational theorem. There are several rationality-relaxed PS methods which work well for such tasks. However, these PS may result in many irrational loops. The proposed method fulfills the rationality by forgetting the reinforced irrational loops. This method can be easily combined with ordinary PS methods and performs well in long term tasks. The simulation results show that the proposed method can learn more efficiently than the conventional PS methods.