mlsanityData to 7 Oct 2026

Cross-Domain Imitation Learning via Optimal Transport

arXiv 2110.03684 ↗First posted 7 Oct 2021cs.LG cs.AI cs.ROcited by 49

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

Abstract (arXiv)

Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology. Comparing trajectories and stationary distributions between the expert and imitation agents is challenging because they live on different systems that may not even have the same dimensionality. We propose Gromov-Wasserstein Imitation Learning (GWIL), a method for cross-domain imitation that uses the Gromov-Wasserstein distance to align and compare states between the different spaces of the agents. Our theory formally characterizes the scenarios where GWIL preserves optimality, revealing its possibilities and limitations. We demonstrate the effectiveness of GWIL in non-trivial continuous control domains ranging from simple rigid transformation of the expert domain to arbitrary transformation of the state-action space.

Key facts. Cited by 49 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 24 of its 47 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

24 of 47 references.

Closest ancestors · 4

Same direction, newest first

  1. 2021Cross-domain Imitation from Observations20 May
  2. 2020Imitation Learning with Sinkhorn Distances20 Aug
  3. 2020Primal Wasserstein Imitation Learning8 Jun
  4. 2019State Alignment-based Imitation Learning21 Nov

Other references · 20

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  3. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  4. 2018DeepMind Control Suitecited by 935
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  6. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  7. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  8. 2017Emergence of Locomotion Behaviours in Rich Environmentscited by 159
  9. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  10. 2018Gromov-Wasserstein Alignment of Word Embedding Spacescited by 119
  11. 2017Third-Person Imitation Learningcited by 103
  12. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 101
8 more
  1. 2018Playing hard exploration games by watching YouTubecited by 98
  2. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 84
  3. 2020CO-Optimal Transportcited by 42
  4. 2018Towards Optimal Transport with Global Invariancescited by 33
  5. 2020Hierarchically Decoupled Imitation for Morphological Transfercited by 30
  6. 2020Aligning Time Series on Incomparable Spacescited by 15
  7. 2020A contribution to Optimal Transport on incomparable spacescited by 14
  8. 2020Time Series Alignment with Global Invariancescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 16; 2024: 11; 2025: 4; 2026: 10.

49 papers.

Sort:

By area:

  1. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
  2. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 74
  3. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 64
  4. 2022Graph Inverse Reinforcement Learning from Diverse Videoscited by 45
  5. 2023Optimal Transport for Offline Imitation Learningcited by 42
  6. 2022Meta Optimal Transportcited by 28
  7. 2023Scalable Optimal Transport Methods in Machine Learning: A Contemporary Surveycited by 27
  8. 2023Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learningcited by 27
  9. 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learningcited by 25
  10. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 24
  11. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddingscited by 14
  12. 2023Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generationcited by 14
37 more
  1. 2023CEIL: Generalized Contextual Imitation Learningcited by 12
  2. 2023Domain Adaptive Imitation Learning with Visual Observationcited by 11
  3. 2023PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulationcited by 9
  4. 2024Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learningcited by 9
  5. 2023Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrationscited by 8
  6. 2023Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learningcited by 6
  7. 2023On the Benefit of Optimal Transport for Curriculum Reinforcement Learningcited by 6
  8. 2024ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transportcited by 6
  9. 2022Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemblecited by 5
  10. 2023Mimicking Better by Matching the Approximate Action Distributioncited by 5
  11. 2023Offline Imitation from Observation via Primal Wasserstein State Occupancy Matchingcited by 5
  12. 2022Co-Imitation: Learning Design and Behaviour by Imitationcited by 3
  13. 2023Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environmentscited by 3
  14. 2024DIDA: Denoised Imitation Learning based on Domain Adaptationcited by 2
  15. 2022Karolos: An Open-Source Reinforcement Learning Framework for Robot-Task Environmentscited by 1
  16. 2023Revisiting invariances and introducing priors in Gromov-Wasserstein distancescited by 1
  17. 2024Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Reviewcited by 1
  18. 2024Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloningcited by 1
  19. 2025Learning human-to-robot handovers through 3D scene reconstructioncited by 1
  20. 2025Expert or not? assessing data quality in offline reinforcement learningcited by 1
  21. 2026Cross-Domain Offline Policy Adaptation via Selective Transition Correctioncited by 1
  22. 2026Semi-Supervised Cross-Domain Imitation Learningcited by 1
  23. 2026ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstrationcited by 1
  24. 2022Hitting time for Markov decision processcited by 0
  25. 2024Strongly Isomorphic Neural Optimal Transport Across Incomparable Spacescited by 0
  26. 2024Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrationscited by 0
  27. 2024Note on computational complexity of the Gromov-Wasserstein distancecited by 0
  28. 2024Know your limits! Optimize the robot's behavior through self-awarenesscited by 0
  29. 2025Minimal Ingredients for Reward Assignment from Expert Demonstrationscited by 0
  30. 2025Data-driven simulator of multi-animal behavior with unknown dynamics via offline and online reinforcement learningcited by 0
  31. 2026Latent Wasserstein Adversarial Imitation Learningcited by 0
  32. 2026Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Criticscited by 0
  33. 2026Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoningcited by 0
  34. 2026Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learningcited by 0
  35. 2026BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfercited by 0
  36. 2026DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learningcited by 0
  37. 2026Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Cross-Domain Imitation Learning with a Dual Structure
  2. 2023Imitation Learning from Observation through Optimal Transport
  3. 2025Generalization Capability for Imitation Learning
  4. 2021Cross Domain Robot Imitation with Invariant Representation
  5. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
  6. 2023On Combining Expert Demonstrations in Imitation Learning via Optimal Transport
  7. 2019Wasserstein Adversarial Imitation Learning
  8. 2024Reward-free World Models for Online Imitation Learning