Approximating Shapley Explanations in Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Beechey, Daniel, Şimşek, Özgür
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918192265297920
author Beechey, Daniel
Şimşek, Özgür
author_facet Beechey, Daniel
Şimşek, Özgür
contents Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety-critical settings. Shapley values from cooperative game theory provide a principled framework for explaining reinforcement learning; however, the computational cost of Shapley explanations is an obstacle to their use. We introduce FastSVERL, a scalable method for explaining reinforcement learning by approximating Shapley values. FastSVERL is designed to handle the unique challenges of reinforcement learning, including temporal dependencies across multi-step trajectories, learning from off-policy data, and adapting to evolving agent behaviours in real time. FastSVERL introduces a practical, scalable approach for principled and rigorous interpretability in reinforcement learning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Approximating Shapley Explanations in Reinforcement Learning
Beechey, Daniel
Şimşek, Özgür
Machine Learning
Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety-critical settings. Shapley values from cooperative game theory provide a principled framework for explaining reinforcement learning; however, the computational cost of Shapley explanations is an obstacle to their use. We introduce FastSVERL, a scalable method for explaining reinforcement learning by approximating Shapley values. FastSVERL is designed to handle the unique challenges of reinforcement learning, including temporal dependencies across multi-step trajectories, learning from off-policy data, and adapting to evolving agent behaviours in real time. FastSVERL introduces a practical, scalable approach for principled and rigorous interpretability in reinforcement learning.
title Approximating Shapley Explanations in Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2511.06094