English

Transfering Hierarchical Structure with Dual Meta Imitation Learning

Robotics 2022-02-22 v2 Artificial Intelligence

Abstract

Hierarchical Imitation Learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations. However, the learned hierarchical structure lacks the mechanism to transfer across multi-tasks or to new tasks, which makes them have to learn from scratch when facing a new situation. Transferring and reorganizing modular sub-skills require fast adaptation ability of the whole hierarchical structure. In this work, we propose Dual Meta Imitation Learning (DMIL), a hierarchical meta imitation learning method where the high-level network and sub-skills are iteratively meta-learned with model-agnostic meta-learning. DMIL uses the likelihood of state-action pairs from each sub-skill as the supervision for the high-level network adaptation, and use the adapted high-level network to determine different data set for each sub-skill adaptation. We theoretically prove the convergence of the iterative training process of DMIL and establish the connection between DMIL and Expectation-Maximization algorithm. Empirically, we achieve state-of-the-art few-shot imitation learning performance on the Meta-world \cite{metaworld} benchmark and competitive results on long-horizon tasks of Kitchen environments.

Keywords

Cite

@article{arxiv.2201.11981,
  title  = {Transfering Hierarchical Structure with Dual Meta Imitation Learning},
  author = {Chongkai Gao and Yizhou Jiang and Feng Chen},
  journal= {arXiv preprint arXiv:2201.11981},
  year   = {2022}
}
R2 v1 2026-06-24T09:06:53.553Z