mlsanityData to 13 Oct 2026

Denoising-based Contractive Imitation Learning

arXiv 2503.15918 ↗First posted 20 Mar 2025cs.LG cs.AIcited by 0

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

Abstract (arXiv)

A fundamental challenge in imitation learning is the covariate shift problem. Existing methods to mitigate covariate shift often require additional expert interactions, access to environment dynamics, or complex adversarial training, which may not be practical in real-world applications. In this paper, we propose a simple yet effective method (DeCIL) to mitigate covariate shift by incorporating a denoising mechanism that enhances the contraction properties of the state transition mapping. Our approach involves training two neural networks: a dynamics model ( f ) that predicts the next state from the current state, and a joint state-action denoising policy network ( d ) that refines this state prediction via denoising and outputs the corresponding action. We provide theoretical analysis showing that the denoising network acts as a local contraction mapping, reducing the error propagation of the state transition and improving stability. Our method is straightforward to implement and can be easily integrated with existing imitation learning frameworks without requiring additional expert data or complex modifications to the training procedure. Empirical results demonstrate that our approach effectively improves success rate of various imitation learning tasks under noise perturbation.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 21 of its 30 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

21 of 30 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery10 Dec
  2. 2024Stable-BC: Controlling Covariate Shift with Stable Behavior Cloning12 Aug
  3. 2023CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning19 Oct
  4. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shift4 Feb
  5. 2020Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning28 Jun
  6. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  7. 2019Imitation Learning as f-Divergence Minimization30 May

Other references · 14

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,760
  2. 2016Generative Adversarial Imitation Learningcited by 1,577
  3. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,175
  4. 2016End to End Learning for Self-Driving Carscited by 1,002
  5. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 584
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 486
  7. 2017DART: Noise Injection for Robust Imitation Learningcited by 188
  8. 2019Self-Supervised Correspondence in Visuomotor Policy Learningcited by 106
  9. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  10. 2019Stabilizing Generative Adversarial Networks: A Surveycited by 57
  11. 2023NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesiscited by 56
  12. 2020Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulationcited by 37
2 more
  1. 2024IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learningcited by 24
  2. 2024Neural Contractive Dynamical Systemscited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learning
  2. 2024DIDA: Denoised Imitation Learning based on Domain Adaptation
  3. 2023Sample-efficient Adversarial Imitation Learning
  4. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
  5. 2024Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
  6. 2025Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
  7. 2023Memory-Consistent Neural Networks for Imitation Learning
  8. 2021Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency