Redefining Counterfactual Explanations For Reinforcement Learning: Overview, Challenges And Opportunities

Abstract

While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-experts are necessary for user trust and human-AI collaboration, the majority of explanation methods for AI are focused on developers and expert users. Counterfactual explanations are local explanations that offer users advice on what can be changed in the input for the output of the black-box model to change. Counterfactuals are user-friendly and provide actionable advice for achieving the desired output from the AI system. While extensively researched in supervised learning, there are few methods applying them to reinforcement learning (RL). In this work, we explore the reasons for the underrepresentation of a powerful explanation method in RL. We start by reviewing the current work in counterfactual explanations in supervised learning. Additionally, we explore the differences between counterfactual explana

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygajcin2022redefining

Related papers

• Experiential Explanations For Reinforcement Learning (2022)2.26
• RACCER: Towards Reachable And Certain Counterfactual Explanations For Reinforcement Learning (2023)0.00
• Ganterfactual-rl: Understanding Reinforcement Learning Agents' Strategies Through Visual Counterfactual Explanations (2023)2.26
• Counterfactual State Explanations For Reinforcement Learning Agents Via Generative Deep Learning (2021)13.23
• Why The Agent Made That Decision: Contrastive Explanation Learning For Reinforcement Learning (2024)0.00
• Learning Impartial Policies For Sequential Counterfactual Explanations Using Deep Reinforcement Learning (2023)0.00
• Explainability In Deep Reinforcement Learning (2020)0.00
• A Survey On Explainable Reinforcement Learning: Concepts, Algorithms, Challenges (2022)0.00