Adversarial Imitation Learning with Trajectorial Augmentation and Correction

Abstract

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.

Accepted in ICRA 2021

References in corpus (10)

• End to End Learning for Self-Driving Cars
• Trust Region Policy Optimization
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Theoretical Models of Learning to Learn
• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
• Data Augmentation Using GANs
• Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation
• Improving Generalization and Stability of Generative Adversarial Networks
• AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
• Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera