USN: a robust imitation learning method against diverse action noise

• Main Authors: Yu, Xingrui, Han, Bo, Tsang, Ivor Wai-Hung
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Learning methods; Realistic scenario
• Online Access: https://hdl.handle.net/10356/179928
• Institution: Nanyang Technological University

Learning from imperfect demonstrations is a crucial challenge in imitation learning (IL). Unlike existing works that still rely on the enormous effort of expert demonstrators, we consider a more cost-effective option for obtaining a large number of demonstrations. That is, hire annotators to label a...