An Approach to Building a Fuzzy Controller that imitates the Internal Behavior of a Pre-trained Deep Reinforcement Learning Model

Abstract

Due to its black-box nature, the internal behavior of a deep reinforcement learning model is challenging to be interpreted by humans. Therefore, we apply fuzzy modeling for the input-output relationships of a deep reinforcement learning model and express these relationships with fuzzy linguistic variables to make linguistic control rules. In this study, we use CartPole as an experiment subject; explain control rules of the model learned by a Deep Q-Network with fuzzy linguistic variables; and try to control the CartPole using those control rules. We use two approaches to construct control rules. One is to construct control rules from input data and the other is to construct control rules from output data. As a result, through experiments, we have confirmed the trade-off between control performance and the number of rules.