ENTL：具身导航轨迹学习器
ENTL: Embodied Navigation Trajectory Learner
AI总结：
本文提出 ENTL，将世界建模、定位与模仿学习统一为序列预测任务，通过无奖励的未来状态向量量化预测预训练，实现少数据下的具身导航与多任务泛化。
摘要：
我们提出了 Embodied Navigation Trajectory Learner（ENTL，具身导航轨迹学习器），这是一种为具身导航提取长序列表示的方法。我们的方法将世界建模、定位和模仿学习统一到单个序列预测任务中。我们使用以当前状态和动作为条件的未来状态向量量化预测来训练模型。ENTL 的通用架构使得时空序列编码器能够共享用于多项具有挑战性的具身任务。我们在导航任务上取得了具有竞争力的性能，所用数据显著少于强基线，同时还能执行定位和未来帧预测（世界建模的代理任务）等辅助任务。我们方法的一个关键特性是，模型在预训练时不需要任何显式奖励信号，这使得所得模型能够泛化到多种任务和环境。
英文摘要：
We propose Embodied Navigation Trajectory Learner (ENTL), a method for extracting long sequence representations for embodied navigation. Our approach unifies world modeling, localization and imitation learning into a single sequence prediction task. We train our model using vector-quantized predictions of future states conditioned on current states and actions. ENTL's generic architecture enables sharing of the spatio-temporal sequence encoder for multiple challenging embodied tasks. We achieve competitive performance on navigation tasks using significantly less data than strong baselines while performing auxiliary tasks such as localization and future frame prediction (a proxy for world modeling). A key property of our approach is that the model is pre-trained without any explicit reward signal, which makes the resulting model generalizable to multiple tasks and environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
