Utilizing Explainability Techniques for Reinforcement Learning Model Assurance

• Main Authors: Tapley, Alexander, Gatesman, Kyle, Robaina, Luis, Bissey, Brett, Weissman, Joseph
• Format: Journal Article
• Language: English
• Published: 27.11.2023
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning
• DOI: 10.48550/arxiv.2311.15838

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.