mlsanityData to 7 Oct 2026

Explaining Reinforcement Learning with Shapley Values

arXiv 2306.05810 ↗First posted 9 Jun 2023cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

For reinforcement learning systems to be widely adopted, their users must understand and trust them. We present a theoretical analysis of explaining reinforcement learning using Shapley values, following a principled approach from game theory for identifying the contribution of individual players to the outcome of a cooperative game. We call this general framework Shapley Values for Explaining Reinforcement Learning (SVERL). Our analysis exposes the limitations of earlier uses of Shapley values in reinforcement learning. We then develop an approach that uses Shapley values to explain agent performance. In a variety of domains, SVERL produces meaningful explanations that match and supplement human intuition.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 4 of its 20 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

4 of 20 references.

References · 4

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2020Shapley explainability on the data manifoldcited by 88
  3. 2021groupShapley: Efficient prediction explanation with Shapley values for feature groupscited by 21
  4. 2021Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 9; 2026: 10.

26 papers.

Sort:

By area:

  1. 2023Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Planscited by 27
  2. 2024Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaborationcited by 12
  3. 2024Towards Multi-dimensional Explanation Alignment for Medical Classificationcited by 6
  4. 2024Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agentcited by 4
  5. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
  6. 2025Behaviour Discovery and Attribution for Explainable Reinforcement Learningcited by 2
  7. 2024Explaining Reinforcement Learning: A Counterfactual Shapley Values Approachcited by 1
  8. 2025Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Modelscited by 1
  9. 2025An Explainable AI Framework for Dynamic Resource Management in Vehicular Network Slicingcited by 1
  10. 2025Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environmentscited by 1
  11. 2025Approximating Shapley Explanations in Reinforcement Learningcited by 1
  12. 2026Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognitioncited by 1
14 more
  1. 2026BXRL: Behavior-Explainable Reinforcement Learningcited by 1
  2. 2026RREDCoT: Segment-Level Reward Redistribution for Reasoning Modelscited by 1
  3. 2024Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learningcited by 0
  4. 2025Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learningcited by 0
  5. 2025Self-Explaining Reinforcement Learning for Mobile Network Resource Allocationcited by 0
  6. 2025Benchmarking Offline Multi-Objective Reinforcement Learning in Critical Carecited by 0
  7. 2025Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air Systemscited by 0
  8. 2026CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Supportcited by 0
  9. 2026Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameterscited by 0
  10. 2026Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systemscited by 0
  11. 2026Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildingscited by 0
  12. 2026Dueling Deep Q-Learning for Intrusion Detectioncited by 0
  13. 2026Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agentscited by 0
  14. 2026IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action Policiescited by 0