mlsanityData to 7 Oct 2026

Causal Transfer for Imitation Learning and Decision Making under Sensor-shift

arXiv 2003.00806 ↗First posted 2 Mar 2020cs.AIcited by 8

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

Abstract (arXiv)

Learning from demonstrations (LfD) is an efficient paradigm to train AI agents. But major issues arise when there are differences between (a) the demonstrator's own sensory input, (b) our sensors that observe the demonstrator and (c) the sensory input of the agent we train. In this paper, we propose a causal model-based framework for transfer learning under such "sensor-shifts", for two common LfD tasks: (1) inferring the effect of the demonstrator's actions and (2) imitation learning. First we rigorously analyze, on the population-level, to what extent the relevant underlying mechanisms (the action effects and the demonstrator policy) can be identified and transferred from the available observations together with prior knowledge of sensor characteristics. And we device an algorithm to infer these mechanisms. Then we introduce several proxy methods which are easier to calculate, estimate from finite data and interpret than the exact solutions, alongside theoretical bounds on their closeness to the exact ones. We validate our two main methods on simulated and semi-real world data.

Key facts. Cited by 8 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 7 of its 27 references that are in the map. First posted on arXiv 2 Mar 2020.

Builds on

7 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2019Causal Confusion in Imitation Learning28 May

Other references · 6

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 276
  3. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  4. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 125
  5. 2013Counterfactual Probabilities: Computational Methods, Bounds and Applicationscited by 67
  6. 2016Experimental and causal view on information integration in autonomous agentscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 4; 2024: 0; 2025: 1.

8 papers.

  1. 2023A Survey on Causal Reinforcement Learningcited by 43
  2. 2022Causal Imitation Learning with Unobserved Confounderscited by 40
  3. 2022Sequential Causal Imitation Learning with Unobserved Confounderscited by 25
  4. 2023Invariant Causal Imitation Learning for Generalizable Policiescited by 15
  5. 2023Causal Imitability Under Context-Specific Independence Relationscited by 6
  6. 2021Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learningcited by 4
  7. 2023Initial State Interventions for Deconfounded Imitation Learningcited by 4
  8. 2025Confounded Causal Imitation Learning with Instrumental Variablescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shift
  2. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  3. 2025Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding
  4. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
  5. 2025Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations
  6. 2021Cross-domain Imitation from Observations
  7. 2022Deconfounding Imitation Learning with Variational Inference
  8. 2023Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations