Year: 2024
Type: preprint
Abstract: This paper introduces a novel approach Counterfactual Shapley Values (CSV), which enhances explainability in reinforcement learning (RL) by integrating counterfactual analysis with Shapley Values. The approach aims to quantify and compare the contributions of different state dimensions to various action choices. To more accurately analyze these impacts, we introduce new characteristic value functions, the ``Counterfactual Difference Characteristic Value" and the ``Average Counterfactual Difference Characteristic Value." These functions help calculate the Shapley values to evaluate the differences in contributions between optimal and non-optimal actions. Experiments across several RL domains, such as GridWorld, FrozenLake, and Taxi, demonstrate the effectiveness of the CSV method. The results show that this method not only improves transparency in complex RL systems but also quantifies the differences across various decisions.
Source: arXiv (Cornell University)
Authors: Shi, Yiwei, Zhang, Qi, McAreavey, Kevin, Liu, Weiru
Institutions: University of Bristol, Tongji University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4403445195