mlsanityData to 7 Oct 2026

DIDA: Denoised Imitation Learning based on Domain Adaptation

arXiv 2404.03382 ↗First posted 4 Apr 2024cs.LG cs.AIcited by 2

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

Abstract (arXiv)

Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where the imitator is required to learn from data with noise that often occurs during the processes of data collection or transmission. Previous IL methods improve the robustness of learned policies by injecting an adversarially learned Gaussian noise into pure expert data or utilizing additional ranking information, but they may fail in the LND setting. To alleviate the above problems, we propose Denoised Imitation learning based on Domain Adaptation (DIDA), which designs two discriminators to distinguish the noise level and expertise level of data, facilitating a feature encoder to learn task-related but domain-agnostic representations. Experiment results on MuJoCo demonstrate that DIDA can successfully handle challenging imitation tasks from demonstrations with various types of noise, outperforming most baseline methods.

Key facts. Cited by 2 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 23 of its 41 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

23 of 41 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations24 Oct
  2. 2022Multi-Task Imitation Learning for Linear Dynamical Systems1 Dec
  3. 2022Robust Imitation Learning against Variations in Environment Dynamics19 Jun
  4. 2021Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality27 Oct
  5. 2021Cross-Domain Imitation Learning via Optimal Transport7 Oct
  6. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraints8 Mar
  7. 2020Robust Imitation Learning from Noisy Demonstrations20 Oct
  8. 2019State Alignment-based Imitation Learning21 Nov
  9. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  10. 2019Imitation Learning as f-Divergence Minimization30 May
  11. 2019Imitation Learning from Imperfect Demonstration27 Jan
  12. 2018An Algorithmic Perspective on Imitation Learning16 Nov

Other references · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2016Generative Adversarial Imitation Learningcited by 1,576
  5. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  6. 2017Third-Person Imitation Learningcited by 103
  7. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regressioncited by 84
  8. 2019Third-Person Visual Imitation Learning via Decoupled Hierarchical Controllercited by 73
  9. 2023HYDRA: Hybrid Robot Actions for Imitation Learningcited by 54
  10. 2022Eliciting Compatible Demonstrations for Multi-Human Imitation Learningcited by 22
  11. 2022NeuroCERIL: Robotic Imitation Learning via Hierarchical Cause-Effect Reasoning in Programmable Attractor Neural Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Semi-Supervised Cross-Domain Imitation Learningcited by 1
  2. 2025A Model-Based Approach to Imitation Learning through Multi-Step Predictionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
  2. 2023Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations
  3. 2025Denoising-based Contractive Imitation Learning
  4. 2023Sample-efficient Adversarial Imitation Learning
  5. 2025Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
  6. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddings
  7. 2022Robust Imitation Learning from Corrupted Demonstrations
  8. 2024Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning