Explainable Reinforcement Learning (XRL) can provide transparency into the decision-making process of a Deep Reinforcement Learning (DRL) model and increase user trust and adoption in real-world use cases. By utilizing XRL techniques, researchers can identify potential vulnerabilities within a trained DRL model prior to deployment, therefore limiting the potential for mission failure or mistakes by the system. This paper introduces the ARLIN (Assured RL Model Interrogation) Toolkit, an open-source Python library that identifies potential vulnerabilities and critical points within trained DRL models through detailed, human-interpretable explainability outputs. To illustrate ARLIN's effectiveness, we provide explainability visualizations and vulnerability analysis for a publicly available DRL model. The open-source code repository is available for download at https://github.com/mitre/arlin.
@article{arxiv.2311.15838,
title = {Utilizing Explainability Techniques for Reinforcement Learning Model Assurance},
author = {Alexander Tapley and Kyle Gatesman and Luis Robaina and Brett Bissey and Joseph Weissman},
journal= {arXiv preprint arXiv:2311.15838},
year = {2023}
}
Comments
9 pages, 8 figures including appendices (A, B, C). Accepted as a poster presentation in the demo track at the "XAI in Action: Past, Present, and Future Applications" workshop at NeurIPS 2023. MITRE Public Release Case Number 23-3095