TraCE: Trajectory Counterfactual Explanation Scores

Autor:	Clark, Jeffrey N., Small, Edward A., Keshtmand, Nawid, Wan, Michelle W. L., Mayoral, Elena Fillola, Werner, Enrico, Bourdeaux, Christopher P., Santos-Rodriguez, Raul
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Computers and Society Mathematics - Metric Geometry
Druh dokumentu:	Working Paper
Popis:	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. Comment: 10 pages, 4 figures, appendix
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2309.15965 Zobrazit plný text záznamu View this record from Arxiv