Overcoming Knowledge Barriers: Online Imitation Learning from Observation with Pretrained World Models

arXiv:2404.18896v1 Announce Type: new
Abstract: Incorporating the successful paradigm of pretraining and finetuning from Computer Vision and Natural Language Processing into decision-making has become increasingly popular in recent years. In this paper, we study Imitation Learning from Observation with pretrained models and find existing approaches such as BCO and AIME face knowledge barriers, specifically the Embodiment Knowledge Barrier (EKB) and the Demonstration Knowledge Barrier (DKB), greatly limiting their performance. The EKB arises when pretrained models lack knowledge about unseen observations, …

arxiv cs.lg imitation learning knowledge observation type world world models