English

Imitation Learning from Observation through Optimal Transport

Robotics 2024-10-07 v2 Artificial Intelligence Machine Learning

Abstract

Imitation Learning from Observation (ILfO) is a setting in which a learner tries to imitate the behavior of an expert, using only observational data and without the direct guidance of demonstrated actions. In this paper, we re-examine optimal transport for IL, in which a reward is generated based on the Wasserstein distance between the state trajectories of the learner and expert. We show that existing methods can be simplified to generate a reward function without requiring learned models or adversarial learning. Unlike many other state-of-the-art methods, our approach can be integrated with any RL algorithm and is amenable to ILfO. We demonstrate the effectiveness of this simple approach on a variety of continuous control tasks and find that it surpasses the state of the art in the IlfO setting, achieving expert-level performance across a range of evaluation domains even when observing only a single expert trajectory without actions.

Keywords

Cite

@article{arxiv.2310.01632,
  title  = {Imitation Learning from Observation through Optimal Transport},
  author = {Wei-Di Chang and Scott Fujimoto and David Meger and Gregory Dudek},
  journal= {arXiv preprint arXiv:2310.01632},
  year   = {2024}
}

Comments

Update to newest version, presented at RLC 2024

R2 v1 2026-06-28T12:38:53.322Z