mlsanityData to 7 Oct 2026

Semi-Supervised Cross-Domain Imitation Learning

arXiv 2602.10793 ↗First posted 11 Feb 2026cs.LG cs.ROcited by 1

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

Abstract (arXiv)

Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised, relying on proxy tasks and explicit alignment, or unsupervised, aligning distributions without paired data, but often unstable. We introduce the Semi-Supervised CDIL (SS-CDIL) setting and propose the first algorithm for SS-CDIL with theoretical justification. Our method uses only offline data, including a small number of target expert demonstrations and some unlabeled imperfect trajectories. To handle domain discrepancy, we propose a novel cross-domain loss function for learning inter-domain state-action mappings and design an adaptive weight function to balance the source and target knowledge. Experiments on MuJoCo and Robosuite show consistent gains over the baselines, demonstrating that our approach achieves stable and data-efficient policy learning with minimal supervision. Our code is available at~ https://github.com/NYCU-RL-Bandits-Lab/CDIL.

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 36 of its 51 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

36 of 51 references.

Closest ancestors · 16

Same direction, newest first

  1. 2024Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning24 Jul
  2. 2024Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning18 Jun
  3. 2024DIDA: Denoised Imitation Learning based on Domain Adaptation4 Apr
  4. 2023Domain Adaptive Imitation Learning with Visual Observation1 Dec
  5. 2023CEIL: Generalized Contextual Imitation Learning26 Jun
  6. 2023Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching5 Mar
  7. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddings24 Sep
  8. 2022Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations20 Jul
  9. 2022Learning from Imperfect Demonstrations via Adversarial Confidence Transfer7 Feb
  10. 2021Cross-Domain Imitation Learning via Optimal Transport7 Oct
  11. 2021Cross Domain Robot Imitation with Invariant Representation13 Sep
  12. 2021IQ-Learn: Inverse soft-Q Learning for Imitation23 Jun
4 more
  1. 2021Cross-domain Imitation from Observations20 May
  2. 2019State Alignment-based Imitation Learning21 Nov
  3. 2019Task-Relevant Adversarial Imitation Learning2 Oct
  4. 2019Imitation Learning from Imperfect Demonstration27 Jan

Other references · 20

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  3. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  4. 2014Convex Optimization: Algorithms and Complexitycited by 569
  5. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  6. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  7. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  8. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  9. 2020Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistencycited by 43
  10. 2024Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learningcited by 42
  11. 2023Cross-Domain Policy Adaptation via Value-Guided Data Filteringcited by 30
  12. 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learningcited by 25
8 more
  1. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 24
  2. 2021Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimizationcited by 18
  3. 2024Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learningcited by 18
  4. 2022Cross-Domain Transfer via Semantic Skill Imitationcited by 17
  5. 2024FlowPG: Action-constrained Policy Gradient with Normalizing Flowscited by 16
  6. 2024One-Shot Imitation under Mismatched Executioncited by 11
  7. 2025Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPscited by 8
  8. 2024Cross Domain Policy Transfer with Effect Cycle-Consistencycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Criticscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Cross-Domain Imitation Learning with a Dual Structure
  2. 2023Invariant Causal Imitation Learning for Generalizable Policies
  3. 2020ADAIL: Adaptive Adversarial Imitation Learning
  4. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learning
  5. 2022Imitation Learning by State-Only Distribution Matching
  6. 2022Discriminator-Guided Model-Based Offline Imitation Learning
  7. 2026On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
  8. 2024Semi-Supervised One-Shot Imitation Learning