Explainability of deep reinforcement learning algorithms in robotic domains by using Layer-wise Relevance PropagationDownload PDF


22 Sept 2022, 12:32 (modified: 26 Oct 2022, 13:58)ICLR 2023 Conference Blind SubmissionReaders: Everyone
Keywords: Explainability, Deep Reinforcement Learning, Graph Network, Layer-wise Relevance Propagation, Robotic
TL;DR: Explaining the policy learned by a deep reinforcement learning algorithm with graph networks as function approximators in robotic environments by using layer-wise relevance propagation technique.
Abstract: A key component to the recent success of reinforcement learning is the introduction of neural networks for representation learning. Doing so allows for solving challenging problems in several domains, one of which is robotics. However, a major criticism of deep reinforcement learning (DRL) algorithms is their lack of explainability and interpretability. This problem is even exacerbated in robotics as they oftentimes cohabitate space with humans, making it imperative to be able to reason about their behaviour. In this paper, we propose to analyze the learned representation in a robotic setting by utilizing graph neural networks. Using the graphical neural networks and Layer-wise Relevance Propagation (LRP), we represent the observations as an entity-relationship to allow us to interpret the learned policy. We evaluate our approach in two environments in MuJoCo. These two environments were delicately designed to effectively measure the value of knowledge gained by our approach to analyzing learned representations. This approach allows us to analyze not only how different parts of the observation space contribute to the decision-making process but also differentiate between policies and their differences in performance. This difference in performance also allows for reasoning about the agent's recovery from faults. These insights are key contributions to explainable deep reinforcement learning in robotic settings.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)
8 Replies