Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
Behavioral cloning (BC) bears a high potential for safe and direct transfer of human skills to robots. However, demonstrations performed by human operators often contain noise or imperfect behaviors that can affect the efficiency of the imitator if left unchecked. In order to allow the imitators to effectively learn from imperfect demonstrations, we propose to employ the robust t-momentum optimization algorithm. This algorithm builds on the Student's t-distribution in order to deal with heavy-tailed data and reduce the effect of outlying observations. We extend the t-momentum algorithm to allow for an adaptive and automatic robustness and show empirically how the algorithm can be used to produce robust BC imitators against datasets with unknown heaviness. Indeed, the imitators trained with the t-momentum-based Adam optimizers displayed robustness to imperfect demonstrations on two different manipulation tasks with different robots and revealed the capability to take advantage of the additional data while reducing the adverse effect of non-optimal behaviors.
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 13 of its 21 references that are in the map. First posted on arXiv 2 Aug 2021.
Builds on
13 of 21 references.
Closest ancestors · 5
Same direction, newest first
- 2020Robust Imitation Learning from Noisy Demonstrations20 Oct
- 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
- 2019VILD: Variational Imitation Learning with Diverse-quality Demonstrations15 Sep
- 2019Imitation Learning from Imperfect Demonstration27 Jan
- 2018Behavioral Cloning from Observation4 May
Other references · 8
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2016Layer Normalizationcited by 5,579
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
- 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
- 2019ROBEL: Robotics Benchmarks for Learning with Low-Cost Robotscited by 70
- 2020t-Soft Update of Target Network for Deep Reinforcement Learningcited by 16
Built on by
Citing papers per year: 2021: 1; 2022: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2022Robust Imitation Learning from Corrupted Demonstrations
- 2020Concurrent Training Improves the Performance of Behavioral Cloning from Observation
- 2022Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation
- 2023Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation
- 2023Aligning Human Intent from Imperfect Demonstrations with Confidence-based Inverse soft-Q Learning
- 2025Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation
- 2022Model-based Offline Imitation Learning with Non-expert Data
- 2026It's Not Just More Demos: Counterfactual Action Sensitivity Coverage for Data-Efficient Robust Robot Imitation