Provably Efficient Third-Person Imitation from Offline Observation

2020/02/27 by Aaron Zweig, Joan Bruna, Zweig, Aaron +1
Computer Science · Mathematics · #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2002.12446

arxiv created 2020/02/27 · openalex publication_date 2020/02/27 · arxiv updated 2020/03/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Domain adaptation in imitation learning represents an essential step towards improving generalizability. However, even in the restricted setting of third-person imitation where transfer is between isomorphic Markov Decision Processes, there are no strong guarantees on the performance of transferred policies. We present problem-dependent, statistical learning guarantees for third-person imitation from observation in an offline setting, and a lower bound on performance in the online setting.

Citations

• DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
• A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

Related

• Cross-domain Imitation from Observations
• Offline Imitation Learning by Controlling the Effective Planning Horizon
• Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
• Online Adaptation for Enhancing Imitation Learning Policies
• Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage