# Robust Imitation Learning from Noisy Demonstrations

arXiv: https://arxiv.org/abs/2010.10181 · HTML: https://mlsanity.com/paper/2010.10181/

## 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.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation](https://mlsanity.com/paper/1811.02790/) (2018)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation](https://mlsanity.com/paper/1708.05144/) (2017)
- [Learning with Symmetric Label Noise: The Importance of Being Unhinged](https://mlsanity.com/paper/1505.07634/) (2015)
- [Imitation Learning from Imperfect Demonstration](https://mlsanity.com/paper/1901.09387/) (2019)
- [Provably Efficient Imitation Learning from Observation Alone](https://mlsanity.com/paper/1905.10948/) (2019)
- [Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences](https://mlsanity.com/paper/2002.09089/) (2020)
- [Wasserstein Adversarial Imitation Learning](https://mlsanity.com/paper/1906.08113/) (2019)
- [On Symmetric Losses for Learning from Corrupted Labels](https://mlsanity.com/paper/1901.09314/) (2019)
- [On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data](https://mlsanity.com/paper/1808.10585/) (2018)
- [VILD: Variational Imitation Learning with Diverse-quality Demonstrations](https://mlsanity.com/paper/1909.06769/) (2019)

## Built on by (most cited first, 26 of 26)

- [Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality](https://mlsanity.com/paper/2110.14754/) (2021)
- [RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning](https://mlsanity.com/paper/2111.02767/) (2021)
- [Robust Imitation Learning against Variations in Environment Dynamics](https://mlsanity.com/paper/2206.09314/) (2022)
- [Towards Robust Offline Reinforcement Learning under Diverse Data Corruption](https://mlsanity.com/paper/2310.12955/) (2023)
- [Benchmarking Constraint Inference in Inverse Reinforcement Learning](https://mlsanity.com/paper/2206.09670/) (2022)
- [Robust Imitation Learning from Corrupted Demonstrations](https://mlsanity.com/paper/2201.12594/) (2022)
- [Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning](https://mlsanity.com/paper/2512.16911/) (2025)
- [Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation](https://mlsanity.com/paper/2209.10149/) (2022)
- [Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2405.00746/) (2024)
- [Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations](https://mlsanity.com/paper/2310.15815/) (2023)
- [Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics](https://mlsanity.com/paper/2606.12365/) (2026)
- [Extraneousness-Aware Imitation Learning](https://mlsanity.com/paper/2210.01379/) (2022)
- [Guided Policy Optimization under Partial Observability](https://mlsanity.com/paper/2505.15418/) (2025)
- [AttenA+: Rectifying Action Inequality in Robotic Foundation Models](https://mlsanity.com/paper/2605.13548/) (2026)
- [Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning](https://mlsanity.com/paper/2108.00625/) (2021)
- [DIDA: Denoised Imitation Learning based on Domain Adaptation](https://mlsanity.com/paper/2404.03382/) (2024)
- [Spatially Visual Perception for End-to-End Robotic Learning](https://mlsanity.com/paper/2411.17458/) (2024)
- [RILe: Reinforced Imitation Learning](https://mlsanity.com/paper/2406.08472/) (2024)
- [Restoring Noisy Demonstration for Imitation Learning With Diffusion Models](https://mlsanity.com/paper/2510.14467/) (2025)
- [ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models](https://mlsanity.com/paper/2510.22201/) (2025)
- [Balance Equation-based Distributionally Robust Offline Imitation Learning](https://mlsanity.com/paper/2511.07942/) (2025)
- [A Symmetric Loss Perspective of Reliable Machine Learning](https://mlsanity.com/paper/2101.01366/) (2021)
- [Sample-efficient Adversarial Imitation Learning](https://mlsanity.com/paper/2303.07846/) (2023)
- [Imitation Learning via Focused Satisficing](https://mlsanity.com/paper/2505.14820/) (2025)
- [Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards](https://mlsanity.com/paper/2604.00258/) (2026)
- [When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited](https://mlsanity.com/paper/2605.17017/) (2026)

## 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.