mlsanityData to 14 Oct 2026

Approximating Shapley Explanations in Reinforcement Learning

arXiv 2511.06094 ↗First posted 8 Nov 2025cs.LGcited by 1

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

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.

Key facts. Cited by 1 paper 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.

Builds on

12 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values12 May

Other references · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  5. 2017Visualizing and Understanding Atari Agentscited by 141
  6. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 125
  7. 2020Shapley explainability on the data manifoldcited by 88
  8. 2019Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attributioncited by 50
  9. 2023Explaining Reinforcement Learning with Shapley Valuescited by 26
  10. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  11. 2021Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026BXRL: Behavior-Explainable Reinforcement Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach
  2. 2025From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation
  3. 2026Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
  4. 2026Action Shapley: A Training Data Selection Metric for World Model in Reinforcement Learning
  5. 2025Balancing Interpretability and Performance in Reinforcement Learning: An Adaptive Spectral Based Linear Approach
  6. 2025Explainable Reinforcement Learning via Temporal Policy Decomposition
  7. 2025A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
  8. 2024XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques