Zero-Shot Offline Imitation Learning via Optimal Transport

Published: 24 Oct 2024, Last Modified: 27 Nov 2024LEAP 2024 PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Imitation Learning, Deep Reinforcement Learning, Optimal Transport
TL;DR: A non-myopic method for zero-shot imitation from arbitrary offline data.
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.
Submission Number: 43
Loading