# Adversarial Imitation Learning with Trajectorial Augmentation and Correction

arXiv: https://arxiv.org/abs/2103.13887 · HTML: https://mlsanity.com/paper/2103.13887/

## Key facts

- Cited by 11 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 30 of its 45 references that are in the map.
- First posted on arXiv 25 Mar 2021.

## Placed in

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

## Builds on (most cited first, 30 of 30)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [One-Shot Visual Imitation Learning via Meta-Learning](https://mlsanity.com/paper/1709.04905/) (2017)
- [Low-Shot Learning from Imaginary Data](https://mlsanity.com/paper/1801.05401/) (2018)
- [Learning Continuous Control Policies by Stochastic Value Gradients](https://mlsanity.com/paper/1510.09142/) (2015)
- [Learning From Noisy Large-Scale Datasets With Minimal Supervision](https://mlsanity.com/paper/1701.01619/) (2017)
- [GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks](https://mlsanity.com/paper/1810.10863/) (2018)
- [Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration](https://mlsanity.com/paper/1707.02920/) (2017)
- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data](https://mlsanity.com/paper/1706.02071/) (2017)
- [Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods](https://mlsanity.com/paper/1903.11260/) (2019)
- [Data Augmentation Using GANs](https://mlsanity.com/paper/1904.09135/) (2019)
- [Zero-Shot Deep Domain Adaptation](https://mlsanity.com/paper/1707.01922/) (2017)
- [Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1804.00644/) (2018)
- [AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers](https://mlsanity.com/paper/1909.04121/) (2019)
- [Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation](https://mlsanity.com/paper/1810.01845/) (2018)
- [Conditional Vehicle Trajectories Prediction in CARLA Urban Environment](https://mlsanity.com/paper/1909.00792/) (2019)
- [Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera](https://mlsanity.com/paper/1812.05841/) (2018)
- [Exact Mean Computation in Dynamic Time Warping Spaces](https://mlsanity.com/paper/1710.08937/) (2017)

## Built on by (most cited first, 11 of 11)

- [Dexterous Manipulation through Imitation Learning: A Survey](https://mlsanity.com/paper/2504.03515/) (2025)
- [Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC](https://mlsanity.com/paper/2109.09910/) (2021)
- [Offline Imitation Learning with Variational Counterfactual Reasoning](https://mlsanity.com/paper/2310.04706/) (2023)
- [Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview](https://mlsanity.com/paper/2403.19916/) (2024)
- [Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division](https://mlsanity.com/paper/2203.14855/) (2022)
- [Output Feedback Tube MPC-Guided Data Augmentation for Robust, Efficient Sensorimotor Policy Learning](https://mlsanity.com/paper/2210.10127/) (2022)
- [Evaluating the Effectiveness of Corrective Demonstrations and a Low-Cost Sensor for Dexterous Manipulation](https://mlsanity.com/paper/2204.07631/) (2022)
- [Simple Noisy Environment Augmentation for Reinforcement Learning](https://mlsanity.com/paper/2305.02882/) (2023)
- [PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions](https://mlsanity.com/paper/2605.09538/) (2026)
- [Dynamic Full-body Motion Agent with Object Interaction via Blending Pre-trained Modular Controllers](https://mlsanity.com/paper/2605.11369/) (2026)
- [A Systematic Approach for Selecting Trajectories for Data Augmentation](https://mlsanity.com/paper/2606.10938/) (2026)

## Abstract (arXiv)

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be easily applied to control tasks due to the sequential nature of the problem. In this work, we introduce a novel augmentation method which preserves the success of the augmented trajectories. To achieve this, we introduce a semi-supervised correction network that aims to correct distorted expert actions. To adequately test the abilities of the correction network, we develop an adversarial data augmented imitation architecture to train an imitation agent using synthetic experts. Additionally, we introduce a metric to measure diversity in trajectory datasets. Experiments show that our data augmentation strategy can improve accuracy and convergence time of adversarial imitation while preserving the diversity between the generated and real trajectories.