mlsanityData to 13 Oct 2026

Causal Explanations for Sequential Decision Making Under Uncertainty

arXiv 2205.15462 ↗First posted 30 May 2022cs.AI cs.MAcited by 2

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

We introduce a novel framework for causal explanations of stochastic, sequential decision-making systems built on the well-studied structural causal model paradigm for causal reasoning. This single framework can identify multiple, semantically distinct explanations for agent actions -- something not previously possible. In this paper, we establish exact methods and several approximation techniques for causal inference on Markov decision processes using this framework, followed by results on the applicability of the exact methods and some run time bounds. We discuss several scenarios that illustrate the framework's flexibility and the results of experiments with human subjects that confirm the benefits of this approach.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 16 of its 59 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

16 of 59 references.

References · 16

  1. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,203
  2. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  3. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  4. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  5. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  6. 2018Explaining Explanations in AIcited by 137
  7. 2015A Modification of the Halpern-Pearl Definition of Causalitycited by 47
  8. 2020The Emerging Landscape of Explainable AI Planning and Decision Makingcited by 44
  9. 2017Explainable Planningcited by 40
  10. 2019Why Does My Model Fail? Contrastive Local Explanations for Retail Forecastingcited by 31
  11. 2018Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behaviorcited by 30
  12. 2020Causality-based Explanation of Classification Outcomescited by 25
4 more
  1. 2018Causal Inference by String Diagram Surgerycited by 23
  2. 2022On the Equivalence of Causal Models: A Category-Theoretic Approachcited by 13
  3. 2020Ranking Policy Decisionscited by 4
  4. 2018Explainable Deterministic MDPscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Automated Discovery of Functional Actual Causes in Complex Environmentscited by 4
  2. 2024Extending Structural Causal Models for Autonomous Vehicles to Simplify Temporal System Construction & Enable Dynamic Interactions Between Agentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022Markov categories, causal theories, and the do-calculus
  2. 2023Reasoning about Causality in Games
  3. 2026An Introduction to Causal Reinforcement Learning
  4. 2024Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making
  5. 2025Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning
  6. 2024A Dynamical View of the Question of Why
  7. 2025HCR-Reasoner: Synergizing Large Language Models and Theory for Human-like Causal Reasoning
  8. 2025Sequential Causal Normal Form Games: Theory, Computation, and Strategic Signaling ↗