mlsanityData to 7 Oct 2026

Robust Imitation Learning from Corrupted Demonstrations

arXiv 2201.12594 ↗First posted 29 Jan 2022cs.LG cs.AI stat.MLcited by 10

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

Abstract (arXiv)

We consider offline Imitation Learning from corrupted demonstrations where a constant fraction of data can be noise or even arbitrary outliers. Classical approaches such as Behavior Cloning assumes that demonstrations are collected by an presumably optimal expert, hence may fail drastically when learning from corrupted demonstrations. We propose a novel robust algorithm by minimizing a Median-of-Means (MOM) objective which guarantees the accurate estimation of policy, even in the presence of constant fraction of outliers. Our theoretical analysis shows that our robust method in the corrupted setting enjoys nearly the same error scaling and sample complexity guarantees as the classical Behavior Cloning in the expert demonstration setting. Our experiments on continuous-control benchmarks validate that our method exhibits the predicted robustness and effectiveness, and achieves competitive results compared to existing imitation learning methods.

Key facts. Cited by 10 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 42 of its 80 references that are in the map. First posted on arXiv 29 Jan 2022.

Builds on

42 of 80 references.

Closest ancestors · 8

Same direction, newest first

  1. 2021Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally25 Feb
  2. 2020Error Bounds of Imitating Policies and Environments22 Oct
  3. 2020Robust Imitation Learning from Noisy Demonstrations20 Oct
  4. 2020Toward the Fundamental Limits of Imitation Learning13 Sep
  5. 2019Imitation Learning via Off-Policy Distribution Matching10 Dec
  6. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  7. 2019Imitation Learning from Imperfect Demonstration27 Jan
  8. 2018An Algorithmic Perspective on Imitation Learning16 Nov

Other references · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  4. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  7. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  9. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  10. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  11. 2020Is Pessimism Provably Efficient for Offline RL?cited by 362
  12. 2019Reinforcement Learning in Healthcare: A Surveycited by 308
22 more
  1. 2021Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimismcited by 275
  2. 2018Learning to Drive in a Daycited by 266
  3. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  4. 2019DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Correctionscited by 254
  5. 2020FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPscited by 232
  6. 2018Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimationcited by 226
  7. 2018Sever: A Robust Meta-Algorithm for Stochastic Optimizationcited by 123
  8. 2014Reinforcement and Imitation Learning via Interactive No-Regret Learningcited by 116
  9. 2020The Importance of Pessimism in Fixed-Dataset Policy Optimizationcited by 99
  10. 2018Robust Estimation via Robust Gradient Estimationcited by 76
  11. 2018Efficient Algorithms for Outlier-Robust Regressioncited by 72
  12. 2020CoinDICE: Off-Policy Confidence Interval Estimationcited by 64
  13. 2017Reinforcement Learning under Model Mismatchcited by 52
  14. 2021Corruption-Robust Offline Reinforcement Learningcited by 51
  15. 2013Loss minimization and parameter estimation with heavy tailscited by 50
  16. 2019Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimationcited by 48
  17. 2014Empirical risk minimization for heavy-tailed lossescited by 37
  18. 2020Robust Compressed Sensing using Generative Modelscited by 33
  19. 2021Robust Policy Gradient against Strong Data Corruptioncited by 30
  20. 2018High Dimensional Robust Sparse Regressioncited by 29
  21. 2019Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learningcited by 23
  22. 2020Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learningcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 2; 2025: 1; 2026: 1.

10 papers.

  1. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 129
  2. 2024GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robotcited by 28
  3. 2022Rank-based Decomposable Losses in Machine Learning: A Surveycited by 26
  4. 2023Towards Robust Offline Reinforcement Learning under Diverse Data Corruptioncited by 24
  5. 2026Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Roboticscited by 4
  6. 2023Unlabeled Imperfect Demonstrations in Adversarial Imitation Learningcited by 3
  7. 2023Theoretical Analysis of Offline Imitation With Supplementary Datasetcited by 2
  8. 2024Spatially Visual Perception for End-to-End Robotic Learningcited by 2
  9. 2025Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrationscited by 2
  10. 2022Dual Generator Offline Reinforcement Learningcited by 1

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. 2022Robust Imitation of a Few Demonstrations with a Backwards Model
  3. 2022Disturbance-Injected Robust Imitation Learning with Task Achievement
  4. 2021Robust Maximum Entropy Behavior Cloning
  5. 2023Imitation Learning from Purified Demonstrations
  6. 2025Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
  7. 2024How to Leverage Diverse Demonstrations in Offline Imitation Learning
  8. 2025Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning