Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation

• Published in: arXiv.org 2021-12
• Main Authors: Jia-Fong Yeh, Chung, Chi-Ming, Hung-Ting, Su, Yi-Ting, Chen, Hsu, Winston H
• Format: Article
• Language: English
• Subjects: Attention; Cloning; Learning; Misalignment; Robotics
• ISSN: 2331-8422

In few-shot imitation learning (FSIL), using behavioral cloning (BC) to solve unseen tasks with few expert demonstrations becomes a popular research direction. The following capabilities are essential in robotics applications: (1) Behaving in compound tasks that contain multiple stages. (2) Retrieving knowledge from few length-variant and misalignment demonstrations. (3) Learning from a different expert. No previous work can achieve these abilities at the same time. In this work, we conduct FSIL problem under the union of above settings and introduce a novel stage conscious attention network (SCAN) to retrieve knowledge from few demonstrations simultaneously. SCAN uses an attention module to identify each stage in length-variant demonstrations. Moreover, it is designed under demonstration-conditioned policy that learns the relationship between experts and agents. Experiment results show that SCAN can learn from different experts without fine-tuning and outperform baselines in complicated compound tasks with explainable visualization.