# Approximating Shapley Explanations in Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.06094 · HTML: https://mlsanity.com/paper/2511.06094/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Placed in

- Deep reinforcement learning methods / [Interpretable and logic-guided RL](https://mlsanity.com/deeprl/interpretable-and-logic-guided-rl/)

## Builds on (most cited first, 12 of 12)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Shapley explainability on the data manifold](https://mlsanity.com/paper/2006.01272/) (2020)
- [Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution](https://mlsanity.com/paper/1912.12191/) (2019)
- [Explaining Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2306.05810/) (2023)
- [Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution](https://mlsanity.com/paper/2401.15866/) (2024)
- [Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning](https://mlsanity.com/paper/2111.02936/) (2021)
- [A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2505.07797/) (2025)

## Built on by (most cited first, 1 of 1)

- [BXRL: Behavior-Explainable Reinforcement Learning](https://mlsanity.com/paper/2603.23738/) (2026)

## Abstract (arXiv)

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.