mlsanityData to 7 Oct 2026

Imitation Learning with Sinkhorn Distances

arXiv 2008.09167 ↗First posted 20 Aug 2020cs.LG cs.RO stat.MLcited by 30

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

Abstract (arXiv)

Imitation learning algorithms have been interpreted as variants of divergence minimization problems. The ability to compare occupancy measures between experts and learners is crucial in their effectiveness in learning from demonstrations. In this paper, we present tractable solutions by formulating imitation learning as minimization of the Sinkhorn distance between occupancy measures. The formulation combines the valuable properties of optimal transport metrics in comparing non-overlapping distributions with a cosine distance cost defined in an adversarially learned feature space. This leads to a highly discriminative critic network and optimal transport plan that subsequently guide imitation learning. We evaluate the proposed approach using both the reward metric and the Sinkhorn distance metric on a number of MuJoCo experiments. For the implementation and reproducing results please refer to the following repository https://github.com/gpapagiannis/sinkhorn-imitation.

Key facts. Cited by 30 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 20 of its 52 references that are in the map. First posted on arXiv 20 Aug 2020.

Builds on

20 of 52 references.

Closest ancestors · 10

Same direction, newest first

  1. 2020Primal Wasserstein Imitation Learning8 Jun
  2. 2020Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration5 Jun
  3. 2019Imitation Learning via Off-Policy Distribution Matching10 Dec
  4. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  5. 2019Wasserstein Adversarial Imitation Learning19 Jun
  6. 2019Sample-efficient Adversarial Imitation Learning from Observation18 Jun
  7. 2019Recent Advances in Imitation Learning from Observation30 May
  8. 2019Imitation Learning as f-Divergence Minimization30 May
  9. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  10. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets6 Sep

Other references · 10

  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2015Trust Region Policy Optimizationcited by 2,503
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  7. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  8. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  9. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  10. 2018Improving GANs Using Optimal Transportcited by 122

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 10; 2024: 7; 2025: 6; 2026: 3.

30 papers.

Sort:

By area:

  1. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 74
  2. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 64
  3. 2021Cross-Domain Imitation Learning via Optimal Transportcited by 49
  4. 2023For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equalcited by 22
  5. 2023What Matters to You? Towards Visual Representation Alignment for Robot Learningcited by 14
  6. 2024Diffusion Imitation from Observationcited by 12
  7. 2023Imitation Learning from Observation with Automatic Discount Schedulingcited by 10
  8. 2024MILES: Making Imitation Learning Easy with Self-Supervisioncited by 9
  9. 2024Rethinking Optimal Transport in Offline Reinforcement Learningcited by 8
  10. 2023Imitation Learning from Observation through Optimal Transportcited by 7
  11. 2025Imitation Learning from a Single Temporally Misaligned Videocited by 7
  12. 2024ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transportcited by 6
18 more
  1. 2024KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidancecited by 6
  2. 2026Failure Identification in Imitation Learning Via Statistical and Semantic Filteringcited by 6
  3. 2023Mimicking Better by Matching the Approximate Action Distributioncited by 5
  4. 2025TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distancecited by 5
  5. 2023Policy Contrastive Imitation Learningcited by 3
  6. 2023Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environmentscited by 3
  7. 2026MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalizationcited by 3
  8. 2024Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Modelscited by 2
  9. 2025Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precisioncited by 2
  10. 2025Expert or not? assessing data quality in offline reinforcement learningcited by 1
  11. 2026ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstrationcited by 1
  12. 2021Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transportcited by 0
  13. 2022Transfer RL via the Undo Maps Formalismcited by 0
  14. 2023On Combining Expert Demonstrations in Imitation Learning via Optimal Transportcited by 0
  15. 2023Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularizationcited by 0
  16. 2024Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminatorcited by 0
  17. 2025On Generalization and Distributional Update for Mimicking Observations with Adequate Explorationcited by 0
  18. 2025Data-driven simulator of multi-animal behavior with unknown dynamics via offline and online reinforcement learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
  2. 2023Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations
  3. 2020Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms
  4. 2021TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
  5. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
  6. 2023Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning
  7. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions
  8. 2019Task-Relevant Adversarial Imitation Learning