Toward Building a Control Method through Verbalizing the Internal Behavior of a Deep Reinforcement Learning Model

Abstract

The internal behaviors of a model acquired by reinforcement learning cannot be understood by humans because the model itself is a black box. Therefore, we apply fuzzy modeling for the input-output relationships of a deep reinforcement learning model, and express the relationships with fuzzy language variables to make lingistic control rules. In this study, using CartPole as an experiment subject, we explain control rules of the model learned by Deep Q-Network in language, and try to control CartPole using those control rules.