@misc{rupf2024:ZILOT,
  title = {Zero-Shot Offline Imitation Learning via Optimal Transport},
  abstract = {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.},
  month = oct,
  year = {2024},
  slug = {rupf2024-zilot},
  author = {Rupf, Thomas and Bagatella, Marco and G{\"u}rtler, Nico and Frey, Jonas and Martius, Georg},
  eprint = {arXiv:2410.08751},
  url = {https://arxiv.org/abs/2410.08751},
  month_numeric = {10}
}