mlsanityData to 7 Oct 2026

Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding

arXiv 2502.07656 ↗First posted 11 Feb 2025cs.LG cs.AIcited by 1

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

Abstract (arXiv)

We propose a general framework for causal Imitation Learning (IL) with hidden confounders, which subsumes several existing settings. Our framework accounts for two types of hidden confounders: (a) variables observed by the expert but not by the imitator, and (b) confounding noise hidden from both. By leveraging trajectory histories as instruments, we reformulate causal IL in our framework into a Conditional Moment Restriction (CMR) problem. We propose DML-IL, an algorithm that solves this CMR problem via instrumental variable regression, and upper bound its imitation gap. Empirical evaluation on continuous state-action environments, including Mujoco tasks, demonstrates that DML-IL outperforms existing causal IL baselines.

Key facts. Cited by 1 paper 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 29 of its 56 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

29 of 56 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Invariant Causal Imitation Learning for Generalizable Policies2 Nov
  2. 2023Initial State Interventions for Deconfounded Imitation Learning29 Jul
  3. 2023Causal Imitability Under Context-Specific Independence Relations1 Jun
  4. 2022Sequential Causal Imitation Learning with Unobserved Confounders12 Aug
  5. 2022Causal Imitation Learning with Unobserved Confounders12 Aug
  6. 2022Sequence Model Imitation Learning with Unobserved Contexts3 Aug
  7. 2022Causal Imitation Learning under Temporally Correlated Noise2 Feb
  8. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shift4 Feb
  9. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Histories28 Oct
  10. 2019Causal Confusion in Imitation Learning28 May

Other references · 19

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  3. 2019Learning by Cheatingcited by 361
  4. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  5. 2019Kernel Instrumental Variable Regressioncited by 118
  6. 2017Imitating Driver Behavior with Generative Adversarial Networkscited by 92
  7. 2015Algorithmic Stability for Adaptive Data Analysiscited by 88
  8. 2019Deep Generalized Method of Moments for Instrumental Variable Analysiscited by 88
  9. 2020Minimax Estimation of Conditional Moment Modelscited by 83
  10. 2013Counterfactual Probabilities: Computational Methods, Bounds and Applicationscited by 67
  11. 2020Learning Deep Features in Instrumental Variable Regressioncited by 65
  12. 2021Shaking the foundations: delusions in sequence models for interaction and controlcited by 61
7 more
  1. 2017Data-driven Planning via Imitation Learningcited by 36
  2. 2020Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approachcited by 31
  3. 2015Optimal Sup-norm Rates and Uniform Inference on Nonlinear Functionals of Nonparametric IV Regressioncited by 30
  4. 2020Valid Causal Inference with (Some) Invalid Instrumentscited by 19
  5. 2021Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decompositioncited by 18
  6. 2020Ivy: Instrumental Variable Synthesis for Causal Inferencecited by 17
  7. 2024Learning Decision Policies with Instrumental Variables through Double Machine Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Learning Long-Context Diffusion Policies via Past-Token Predictioncited by 28

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. 2026Scalable Causal Imitation Learning
  4. 2020Causal Transfer for Imitation Learning and Decision Making under Sensor-shift
  5. 2025Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations
  6. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
  7. 2021On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning
  8. 2021Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage