mlsanityData to 7 Oct 2026

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery

arXiv 2402.18910 ↗First posted 29 Feb 2024cs.LG cs.AI stat.MEcited by 0

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

Abstract (arXiv)

Causality has been combined with machine learning to produce robust representations for domain generalization. Most existing methods of this type require massive data from multiple domains to identify causal features by cross-domain variations, which can be expensive or even infeasible and may lead to misidentification in some cases. In this work, we make a different attempt by leveraging the demonstration data distribution to discover the causal features for a domain generalizable policy. We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution via causal discovery. Our framework can achieve domain generalizable imitation learning with only single-domain data and serve as a complement for cross-domain variation-based methods under non-structural assumptions on the underlying causal models. Our empirical study in various control tasks shows that the proposed framework evidently improves the domain generalization performance and has comparable performance to the expert in the original domain simultaneously.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 17 of its 45 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

17 of 45 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Invariant Causal Imitation Learning for Generalizable Policies2 Nov
  2. 2022Sequential Causal Imitation Learning with Unobserved Confounders12 Aug
  3. 2022Causal Imitation Learning with Unobserved Confounders12 Aug
  4. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shift4 Feb
  5. 2019Causal Confusion in Imitation Learning28 May

Other references · 12

  1. 2019Invariant Risk Minimizationcited by 1,832
  2. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  3. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  4. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  5. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  6. 2017One-Shot Imitation Learningcited by 232
  7. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  8. 2020Invariant Risk Minimization Gamescited by 188
  9. 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 182
  10. 2020Invariant Causal Prediction for Block MDPscited by 104
  11. 2013Directed Cyclic Graphical Representations of Feedback Modelscited by 27
  12. 2016Interpreting Latent Variables in Factor Models via Convex Optimizationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations
  2. 2023Interpretable Imitation Learning with Dynamic Causal Relations
  3. 2021Cross-domain Imitation from Observations
  4. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddings
  5. 2025Generalization Capability for Imitation Learning
  6. 2026Semi-Supervised Cross-Domain Imitation Learning
  7. 2023Causal Imitability Under Context-Specific Independence Relations
  8. 2025Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding