TraCE: Trajectory Counterfactual Explanation Scores
This provides a tool for researchers and practitioners to assess progress in complex sequential scenarios, though it appears incremental as it extends existing counterfactual explanation methods to new domains.
The paper tackles the problem of evaluating progress in sequential decision-making tasks by introducing TraCE scores, a model-agnostic framework that condenses progress into a single value, demonstrated in healthcare and climate change case studies.
Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box classifier. In this paper, we propose to extend the use of counterfactuals to evaluate progress in sequential decision making tasks. To this end, we introduce a model-agnostic modular framework, TraCE (Trajectory Counterfactual Explanation) scores, which is able to distill and condense progress in highly complex scenarios into a single value. We demonstrate TraCE's utility across domains by showcasing its main properties in two case studies spanning healthcare and climate change.