Explainable Artificial Intelligence (XAI) For Increasing User Trust In Deep Reinforcement Learning Driven Autonomous Systems

Abstract

We consider the problem of providing users of deep Reinforcement Learning (RL) based systems with a better understanding of when their output can be trusted. We offer an explainable artificial intelligence (XAI) framework that provides a three-fold explanation: a graphical depiction of the systems generalization and performance in the current game state, how well the agent would play in semantically similar environments, and a narrative explanation of what the graphical information implies. We created a user-interface for our XAI framework and evaluated its efficacy via a human-user experiment. The results demonstrate a statistically significant increase in user trust and acceptance of the AI system with explanation, versus the AI system without explanation.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydruce2021explainable

Related papers

• Explainability In Deep Reinforcement Learning (2020)0.00
• Domain-level Explainability -- A Challenge For Creating Trust In Superhuman AI Strategies (2020)0.00
• Explainable Reinforcement Learning: A Survey (2020)0.00
• Explainability In Deep Reinforcement Learning, A Review Into Current Methods And Applications (2022)12.33
• Explainable Reinforcement Learning For Broad-xai: A Conceptual Framework And Survey (2021)0.00
• Utilizing Explainability Techniques For Reinforcement Learning Model Assurance (2023)2.16
• A Survey Of Explainable Reinforcement Learning: Targets, Methods And Needs (2025)0.00
• Abstracted Trajectory Visualization For Explainability In Reinforcement Learning (2024)2.26