paper-with-me

Papers

Zero-Shot Offline Imitation Learning via Optimal Transport

2024-10-11 · Thomas Rupf, Marco Bagatella, Nico Gürtler, Jonas Frey, Georg Martius

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.

📄 PDF Abstract BibTeX arXiv:2410.08751

Code (1)

martius-lab/zilot 공식 구현 jax

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

Improving Zero-Shot Offline RL via Behavioral Task Sampling

2026-04-28 · Nazim Bendib, Nicolas Perrin-Gilbert, Olivier Sigaud arxiv

Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction. The standard approach to this problem trains task-conditioned policies …

Zero-shot GeneralizationReinforcement LearningOffline RL

Zero-Shot Recognition via Optimal Transport

2019-10-20 · Wenlin Wang, Hongteng Xu, Guoyin Wang, Wenqi Wang 외

We propose an optimal transport (OT) framework for generalized zero-shot learning (GZSL), seeking to distinguish samples for both seen and unseen classes, with the assist of auxiliary attributes. The discrepancy between …

AttributeGeneralized Zero-Shot LearningZero-Shot Learning

Align Your Intents: Offline Imitation Learning via Optimal Transport

2024-02-20 · Maksim Bobrin, Nazar Buzun, Dmitrii Krylov, Dmitry V. Dylov

Offline Reinforcement Learning (RL) addresses the problem of sequential decision-making by learning optimal policy through pre-collected data, without interacting with the environment. As yet, it has remained somewhat im…

D4RLDecision MakingImitation LearningOffline RL+2

ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts

2023-01-28 · Kwanyoung Kim, Yujin Oh, Jong Chul Ye

Recent success of large-scale Contrastive Language-Image Pre-training (CLIP) has led to great promise in zero-shot semantic segmentation by transferring image-text aligned knowledge to pixel-level classification. However…

SegmentationSemantic SegmentationZero Shot SegmentationZero-Shot Semantic Segmentation

Transductive Universal Transport for Zero-Shot Action Recognition

2021-09-29 · Pascal Mettes

This work addresses the problem of recognizing action categories in videos for which no training examples are available. The current state-of-the-art enables such a zero-shot recognition by learning universal mappings fr…

Action RecognitionObjectPositionTemporal Localization+3