SubIQ: Inverse Soft-Q Learning for Offline Imitation with Suboptimal Demonstrations

arXiv:2402.13147v1 Announce Type: new
Abstract: We consider offline imitation learning (IL), which aims to mimic the expert's behavior from its demonstration without further interaction with the environment. One of the main challenges in offline IL is dealing with the limited support of expert demonstrations that cover only a small fraction of the state-action spaces. In this work, we consider offline IL, where expert demonstrations are limited but complemented by a larger set of sub-optimal demonstrations of lower expertise levels. Most …

abstract arxiv behavior challenges cs.ai cs.lg environment expert imitation learning offline small support the environment type