mlsanityData to 14 Oct 2026

Robust Imitation Learning from Noisy Demonstrations

arXiv 2010.10181 ↗First posted 20 Oct 2020stat.ML cs.AI cs.LGcited by 26

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

Abstract (arXiv)

Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk with a symmetric loss. Based on this theoretical finding, we then propose a new imitation learning method that optimizes the classification risk by effectively combining pseudo-labeling with co-training. Unlike existing methods, our method does not require additional labels or strict assumptions about noise distributions. Experimental results on continuous-control benchmarks show that our method is more robust compared to state-of-the-art methods.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 38 references that are in the map. First posted on arXiv 20 Oct 2020.

Builds on

19 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences21 Feb
  2. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  3. 2019VILD: Variational Imitation Learning with Diverse-quality Demonstrations15 Sep
  4. 2019Wasserstein Adversarial Imitation Learning19 Jun
  5. 2019Provably Efficient Imitation Learning from Observation Alone27 May
  6. 2019Imitation Learning from Imperfect Demonstration27 Jan

Other references · 13

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2016Generative Adversarial Imitation Learningcited by 1,597
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  5. 2018Which Training Methods for GANs do actually Converge?cited by 679
  6. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  7. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  8. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  9. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 204
  10. 2017Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximationcited by 121
  11. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  12. 2019On Symmetric Losses for Learning from Corrupted Labelscited by 53
1 more
  1. 2018On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Datacited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 3; 2024: 4; 2025: 6; 2026: 4.

26 papers.

Sort:

By area:

  1. 2021Confidence-Aware Imitation Learning from Demonstrations with Varying Optimalitycited by 44
  2. 2021RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learningcited by 31
  3. 2022Robust Imitation Learning against Variations in Environment Dynamicscited by 26
  4. 2023Towards Robust Offline Reinforcement Learning under Diverse Data Corruptioncited by 24
  5. 2022Benchmarking Constraint Inference in Inverse Reinforcement Learningcited by 18
  6. 2022Robust Imitation Learning from Corrupted Demonstrationscited by 10
  7. 2025Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuningcited by 8
  8. 2022Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulationcited by 7
  9. 2024Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learningcited by 6
  10. 2023Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrationscited by 4
  11. 2026Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Roboticscited by 4
  12. 2022Extraneousness-Aware Imitation Learningcited by 3
14 more
  1. 2025Guided Policy Optimization under Partial Observabilitycited by 3
  2. 2026AttenA+: Rectifying Action Inequality in Robotic Foundation Modelscited by 3
  3. 2021Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learningcited by 2
  4. 2024DIDA: Denoised Imitation Learning based on Domain Adaptationcited by 2
  5. 2024Spatially Visual Perception for End-to-End Robotic Learningcited by 2
  6. 2024RILe: Reinforced Imitation Learningcited by 1
  7. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Modelscited by 1
  8. 2025ACG: Action Coherence Guidance for Flow-based Vision-Language-Action modelscited by 1
  9. 2025Balance Equation-based Distributionally Robust Offline Imitation Learningcited by 1
  10. 2021A Symmetric Loss Perspective of Reliable Machine Learningcited by 0
  11. 2023Sample-efficient Adversarial Imitation Learningcited by 0
  12. 2025Imitation Learning via Focused Satisficingcited by 0
  13. 2026Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewardscited by 0
  14. 2026When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisitedcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Imitation Learning from Purified Demonstrations
  2. 2022Disturbance-Injected Robust Imitation Learning with Task Achievement
  3. 2022Robust Imitation of a Few Demonstrations with a Backwards Model
  4. 2025A Model-Based Approach to Imitation Learning through Multi-Step Predictions
  5. 2023Selective Sampling and Imitation Learning via Online Regression
  6. 2021Learning from Imperfect Demonstrations from Agents with Varying Dynamics
  7. 2023Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations
  8. 2021Robust Maximum Entropy Behavior Cloning