Self-Supervised Discovering of Interpretable Features for Reinforcement Learning

Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the decision-making process is generally not transparent. The lack of interpretability hinders the applicability in safety-critical scenarios. While several methods have attempted to interpret vision-based RL, most come without detailed explanation for the agent's behaviour. In this paper, we propose a self-supervised interpretable framework, which can discover causal features to enable easy interpretation of RL even for non-experts. Specifically, a self-supervised interpretable network is employed to produce fine-grained masks for highlighting task-relevant information, which constitutes most evidence for the agent's decisions. We verify and evaluate our method on several Atari-2600 games and Duckietown, which is a challenging self-driving car simulator environment. The results show that our method renders causal explanations and empirical evidences about how the agent makes decisions and why the agent performs well or badly. Overall, our method provides valuable insight into the decision-making process of RL. In addition, our method does not use any external labelled data, and thus demonstrates the possibility to learn high-quality mask through a self-supervised manner, which may shed light on new paradigms for label-free vision learning such as self-supervised segmentation and detection.