mlsanityData to 7 Oct 2026

Causal Imitation Learning with Unobserved Confounders

arXiv 2208.06267 ↗First posted 12 Aug 2022cs.LG cs.AIcited by 40

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

One of the common ways children learn is by mimicking adults. Imitation learning focuses on learning policies with suitable performance from demonstrations generated by an expert, with an unspecified performance measure, and unobserved reward signal. Popular methods for imitation learning start by either directly mimicking the behavior policy of an expert (behavior cloning) or by learning a reward function that prioritizes observed expert trajectories (inverse reinforcement learning). However, these methods rely on the assumption that covariates used by the expert to determine her/his actions are fully observed. In this paper, we relax this assumption and study imitation learning when sensory inputs of the learner and the expert differ. First, we provide a non-parametric, graphical criterion that is complete (both necessary and sufficient) for determining the feasibility of imitation from the combinations of demonstration data and qualitative assumptions about the underlying environment, represented in the form of a causal model. We then show that when such a criterion does not hold, imitation could still be feasible by exploiting quantitative knowledge of the expert trajectories. Finally, we develop an efficient procedure for learning the imitating policy from experts' trajectories.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 9 of its 47 references that are in the map. First posted on arXiv 12 Aug 2022.

Builds on

9 of 47 references.

Closest ancestors · 3

Same direction, newest first

  1. 2020Causal Transfer for Imitation Learning and Decision Making under Sensor-shift2 Mar
  2. 2019Causal Confusion in Imitation Learning28 May
  3. 2018An Algorithmic Perspective on Imitation Learning16 Nov

Other references · 6

  1. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  2. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  3. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 276
  4. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  5. 2017Boundary-Seeking Generative Adversarial Networkscited by 27
  6. 2017Causal Generative Neural Networkscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 12; 2025: 10; 2026: 5.

40 papers.

Sort:

By area:

  1. 2023A Survey on Causal Reinforcement Learningcited by 43
  2. 2023Causal Reinforcement Learning: A Surveycited by 22
  3. 2023Passive learning of active causal strategies in agents and language modelscited by 21
  4. 2024Neural Causal Abstractionscited by 20
  5. 2023Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approachcited by 17
  6. 2023Invariant Causal Imitation Learning for Generalizable Policiescited by 15
  7. 2024Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Searchcited by 12
  8. 2023Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractionscited by 11
  9. 2024Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learningcited by 10
  10. 2023Causal Imitability Under Context-Specific Independence Relationscited by 6
  11. 2023MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignmentcited by 6
  12. 2025Automatic Reward Shaping from Confounded Offline Datacited by 6
28 more
  1. 2025Confounding Robust Deep Reinforcement Learning: A Causal Approachcited by 6
  2. 2024Causality from Bottom to Top: A Surveycited by 5
  3. 2023Initial State Interventions for Deconfounded Imitation Learningcited by 4
  4. 2023A Data-Driven State Aggregation Approach for Dynamic Discrete Choice Modelscited by 3
  5. 2024BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learningcited by 3
  6. 2025Reinforcement Learning with Continuous Actions Under Unmeasured Confoundingcited by 3
  7. 2023Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Featurescited by 2
  8. 2026Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Rewardcited by 2
  9. 2022NeuroCERIL: Robotic Imitation Learning via Hierarchical Cause-Effect Reasoning in Programmable Attractor Neural Networkscited by 1
  10. 2023Active and Passive Causal Inference Learningcited by 1
  11. 2024Limitations of Agents Simulated by Predictive Modelscited by 1
  12. 2024Why Online Reinforcement Learning is Causalcited by 1
  13. 2024Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneitycited by 1
  14. 2024Exploring and Addressing Reward Confusion in Offline Preference Learningcited by 1
  15. 2025Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confoundingcited by 1
  16. 2025Text-Driven Causal Representation Learning for Source-Free Domain Generalizationcited by 1
  17. 2025Learning Causal Structure Distributions for Robust Planningcited by 1
  18. 2025On Transportability for Structural Causal Banditscited by 1
  19. 2024The Virtues of Pessimism in Inverse Reinforcement Learningcited by 0
  20. 2024DIGIC: Domain Generalizable Imitation Learning by Causal Discoverycited by 0
  21. 2024Disentangled Representations for Causal Cognitioncited by 0
  22. 2025A Relative Ignorability Framework for Decision-Relevant Observability in Control Theory and Reinforcement Learningcited by 0
  23. 2025Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Criticcited by 0
  24. 2025Breaking Habits: On the Role of the Advantage Function in Learning Causal State Representationscited by 0
  25. 2026Causal Imitation Learning Under Measurement Error and Distribution Shiftcited by 0
  26. 2026Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmarkcited by 0
  27. 2026Quantifying Potential Observation Missingness in Inverse Reinforcement Learningcited by 0
  28. 2026Scalable Causal Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Confounded Causal Imitation Learning with Instrumental Variables
  2. 2022Deconfounding Imitation Learning with Variational Inference
  3. 2022Sequential Causal Imitation Learning with Unobserved Confounders
  4. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shift
  5. 2021Imitation Learning by Reinforcement Learning
  6. 2024A Bayesian Solution To The Imitation Gap
  7. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  8. 2021On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning