Host: Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT)
In order to realize intelligent agent such as autonomous mobile robots, Reinforcement Learning is one of the necessary techniques in the control system. It is desirable in terms of knowledge or skill acquisition of agents that reinforcement learning is based only upon rewards concept instead of teaching signal. However, there exist many problems to apply reinforcement learning to actual problems. The most severe problem is huge iterations in learning process. Our motivation is to utilize appropriately instructions that we can give to the reinforcement learning agent along with main rewards in order to haste the learning process and to attain valid learning performance for preparation of segmentation. In this study, we propose an instruction approach for reinforcement learning agents based on sub-rewards and forgetting mechanisms. Through numerical experiments of the grid world task and the mountain car task, we show validness of the proposed approach in terms of learning speed and accuracy.