Ixdrl: A Novel Explainable Deep Reinforcement Learning Toolkit Based On Analyses Of Interestingness

Abstract

In recent years, advances in deep learning have resulted in a plethora of successes in the use of reinforcement learning (RL) to solve complex sequential decision tasks with high-dimensional inputs. However, existing systems lack the necessary mechanisms to provide humans with a holistic view of their competence, presenting an impediment to their adoption, particularly in critical applications where the decisions an agent makes can have significant consequences. Yet, existing RL-based systems are essentially competency-unaware in that they lack the necessary interpretation mechanisms to allow human operators to have an insightful, holistic view of their competency. Towards more explainable Deep RL (xDRL), we propose a new framework based on analyses of interestingness. Our tool provides various measures of RL agent competence stemming from interestingness analysis and is applicable to a wide range of RL algorithms, natively supporting the popular RLLib toolkit. We showcase the use of o

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keysequeira2023ixdrl

Related papers

• Global And Local Analysis Of Interestingness For Competency-aware Deep Reinforcement Learning (2022)0.00
• Interestingness Elements For Explainable Reinforcement Learning: Understanding Agents' Capabilities And Limitations (2019)14.55
• Explainability In Deep Reinforcement Learning (2020)0.00
• A Survey On Explainable Reinforcement Learning: Concepts, Algorithms, Challenges (2022)0.00
• Xrl-bench: A Benchmark For Evaluating And Comparing Explainable Reinforcement Learning Techniques (2024)0.00
• Explainability In Deep Reinforcement Learning, A Review Into Current Methods And Applications (2022)12.33
• Utilizing Explainability Techniques For Reinforcement Learning Model Assurance (2023)2.16
• A Survey Of Explainable Reinforcement Learning: Targets, Methods And Needs (2025)0.00