A Study on Evaluation of Eligibility Trace in Instruction Method for Fuzzy Q-learning Agent

Abstract

In order to realize intelligent agents such as autonomous mobile robots, Reinforcement Learning is one of the necessary techniques in control systems. It is desirable in terms of knowledge or skill acquisition of agents that reinforcement learning is based only upon rewards instead of teaching signals. However, there exist many problems to apply reinforcement learning to real-world tasks. The most severe problem is a huge number of iterations in the learning phase. In this study, we proposed an instruction approach for reinforcement learning agents based on the eligibility trace, sub-reward and forgetting mechanisms. Through numerical experiments, we show the validness of the proposed approach in terms of learning speed and accuracy.