Easy-IIL: Reducing Human Operational Burden in Interactive Imitation Learning via Assistant Experts
Chengjie Zhang, Chao Tang, Wenlong Dong, Dehao Huang, Aoxiang Gu, and Hong Zhang

TL;DR
Easy-IIL introduces a framework that minimizes human effort in interactive imitation learning by using a model-based assistant expert, requiring only a single demonstration and critical interventions, while maintaining high performance.
Contribution
It proposes leveraging off-the-shelf model-based imitation methods as assistant experts to drastically reduce human involvement in IIL, with minimal demonstration and intervention.
Findings
Significantly reduces human operational burden
Maintains performance comparable to mainstream IIL methods
User studies show reduced subjective workload
Abstract
Interactive Imitation Learning (IIL) typically relies on extensive human involvement for both offline demonstration and online interaction. Prior work primarily focuses on reducing human effort in passive monitoring rather than active operation. Interestingly, structured model-based imitation approaches achieve comparable performance with significantly fewer demonstrations than end-to-end imitation learning policies in the low-data regime. However, these methods are typically surpassed by end-to-end policies as the data increases. Leveraging this insight, we propose Easy-IIL, a framework that utilizes off-the-shelf model-based imitation methods as an assistant expert to replace active human operation for the majority of data collection. The human expert only provides a single demonstration to initialize the assistant expert and intervenes in critical states where the task is approaching…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Robot Manipulation and Learning · Human Pose and Action Recognition
