Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities
This work tackles the problem of improving transparency and user trust in AI systems for non-experts by adapting counterfactual explanations to reinforcement learning, though it is incremental as it builds on existing supervised learning approaches.
The paper addresses the underrepresentation of counterfactual explanations in reinforcement learning by reviewing existing methods in supervised learning, identifying key challenges for RL adoption, and proposing a redefinition and research directions for implementing counterfactuals in RL.
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 explanations in supervised learning and RL and identify the main challenges that prevent the adoption of methods from supervised in reinforcement learning. Finally, we redefine counterfactuals for RL and propose research directions for implementing counterfactuals in RL.