DIDA: Denoised Imitation Learning based on Domain Adaptation

arXiv:2404.03382v1 Announce Type: new
Abstract: Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where the imitator is required to learn from data with noise that often occurs during the processes of data collection or transmission. Previous IL methods improve the robustness of learned policies by injecting an adversarially learned Gaussian noise into pure expert data or …

abstract applications arxiv cs.ai cs.lg data datasets domain domain adaptation focus imitation learning learn low noise quality skills type work world