mlsanityData to 7 Oct 2026

Noise-Guided Transport for Imitation Learning

arXiv 2509.26294 ↗First posted 30 Sep 2025cs.LG cs.AIcited by 0

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

Abstract (arXiv)

We consider imitation learning in the low-data regime, where only a limited number of expert demonstrations are available. In this setting, methods that rely on large-scale pretraining or high-capacity architectures can be difficult to apply, and efficiency with respect to demonstration data becomes critical. We introduce Noise-Guided Transport (NGT), a lightweight off-policy method that casts imitation as an optimal transport problem solved via adversarial training. NGT requires no pretraining or specialized architectures, incorporates uncertainty estimation by design, and is easy to implement and tune. Despite its simplicity, NGT achieves strong performance on challenging continuous control tasks, including high-dimensional Humanoid tasks, under ultra-low data regimes with as few as 20 transitions.

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 51 of its 72 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

51 of 72 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024Adversarial Imitation Learning via Boosting12 Apr
  2. 2023DiffAIL: Diffusion Adversarial Imitation Learning11 Dec
  3. 2023Imitation Learning from Observation through Optimal Transport2 Oct
  4. 2023Mimicking Better by Matching the Approximate Action Distribution16 Jun
  5. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transport30 Jun
  6. 2021Off-Policy Imitation Learning from Observations25 Feb
  7. 2020Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning28 Jun
  8. 2020Primal Wasserstein Imitation Learning8 Jun
  9. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  10. 2019Wasserstein Adversarial Imitation Learning19 Jun
  11. 2019Imitation Learning as f-Divergence Minimization30 May
  12. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation16 May
2 more
  1. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  2. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets6 Sep

Other references · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2016Layer Normalizationcited by 5,579
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  8. 2017Deep reinforcement learning from human preferencescited by 3,846
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  10. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  11. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  12. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
25 more
  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2023Mastering Diverse Domains through World Modelscited by 1,193
  5. 2018Exploration by Random Network Distillationcited by 966
  6. 2018DeepMind Control Suitecited by 935
  7. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  8. 2017Wasserstein GANcited by 635
  9. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  10. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
  11. 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 218
  12. 2018Sorting out Lipschitz function approximationcited by 211
  13. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 167
  14. 2024WARM: On the Benefits of Weight Averaged Reward Modelscited by 145
  15. 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RLcited by 136
  16. 2014Generalization and Exploration via Randomized Value Functionscited by 112
  17. 2020Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networkscited by 73
  18. 2018Improving Regression Performance with Distributional Lossescited by 66
  19. 2025The GAN is dead; long live the GAN! A Modern GAN Baselinecited by 57
  20. 2023Anti-Exploration by Random Network Distillationcited by 49
  21. 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 45
  22. 2021Offline Reinforcement Learning as Anti-Explorationcited by 44
  23. 2023Some Fundamental Aspects about Lipschitz Continuity of Neural Networkscited by 25
  24. 2024Imitating Language via Scalable Inverse Reinforcement Learningcited by 21
  25. 2024Supervised Fine-Tuning as Inverse Reinforcement Learningcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning via Implicit Imitation Guidance
  2. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions
  3. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
  4. 2026Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics
  5. 2025Generalization Capability for Imitation Learning
  6. 2025Denoising-based Contractive Imitation Learning
  7. 2025Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
  8. 2026Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learning