# Self-Supervised Discovering of Interpretable Features for Reinforcement Learning

arXiv: https://arxiv.org/abs/2003.07069 · HTML: https://mlsanity.com/paper/2003.07069/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 5 of 5)

- [Explainable Deep Reinforcement Learning: State of the Art and Challenges](https://mlsanity.com/paper/2301.09937/) (2023)
- [A Survey of Explainable Reinforcement Learning](https://mlsanity.com/paper/2202.08434/) (2022)
- [Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey](https://mlsanity.com/paper/2108.09003/) (2021)
- [Learning Symbolic Rules for Interpretable Deep Reinforcement Learning](https://mlsanity.com/paper/2103.08228/) (2021)
- [Symbolic Distillation for Learned TCP Congestion Control](https://mlsanity.com/paper/2210.16987/) (2022)

## Abstract (arXiv)

Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent's decision-making process is generally not transparent. The lack of interpretability hinders the applicability of RL in safety-critical scenarios. While several methods have attempted to interpret vision-based RL, most come without detailed explanation for the agent's behavior. In this paper, we propose a self-supervised interpretable framework, which can discover interpretable features to enable easy understanding of RL agents even for non-experts. Specifically, a self-supervised interpretable network (SSINet) is employed to produce fine-grained attention 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 as well as Duckietown, which is a challenging self-driving car simulator environment. The results show that our method renders empirical evidences about how the agent makes decisions and why the agent performs well or badly, especially when transferred to novel scenes. Overall, our method provides valuable insight into the internal decision-making process of vision-based 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.