Zero-Shot Offline Imitation Learning via Optimal Transport

Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling imitation with a high-level goal selector, and a low-level goal-conditioned policy. However, this framework can suffer from myopic behavior: the agent's immediate actions towards achieving individual goals may undermine long-term objectives. We introduce a novel method that mitigates this issue by directly optimizing the occupancy matching objective that is intrinsic to imitation learning. We propose to lift a goal-conditioned value function to a distance between occupancies, which are in turn approximated via a learned world model. The resulting method can learn from offline, suboptimal data, and is capable of non-myopic, zero-shot imitation, as we demonstrate in complex, continuous benchmarks.

@article{rupf2025_2410.08751,
  title={ Zero-Shot Offline Imitation Learning via Optimal Transport },
  author={ Thomas Rupf and Marco Bagatella and Nico Gürtler and Jonas Frey and Georg Martius },
  journal={arXiv preprint arXiv:2410.08751},
  year={ 2025 }
}