Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learning

2023/11/01 by Emmanouil Panagiotou, Panagiotou, E., Eirini Ntoutsi +1
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2311.00523

openalex publication_date 2023/11/01 · openalex created_date 2023/11/03 · openalex updated_date 2026/07/28

Abstract

In the field of explainable Artificial Intelligence (XAI), sequential counterfactual (SCF) examples are often used to alter the decision of a trained classifier by implementing a sequence of modifications to the input instance. Although certain test-time algorithms aim to optimize for each new instance individually, recently Reinforcement Learning (RL) methods have been proposed that seek to learn policies for discovering SCFs, thereby enhancing scalability. As is typical in RL, the formulation of the RL problem, including the specification of state space, actions, and rewards, can often be ambiguous. In this work, we identify shortcomings in existing methods that can result in policies with undesired properties, such as a bias towards specific actions. We propose to use the output probabilities of the classifier to create a more informative reward, to mitigate this effect.

Related

• Counterfactual Explanation Policies in RL
• Class-Aware Reinforcement Learning for Counterfactual Explanation Generation
• GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations
• Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities
• RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning