让世界模型学会随时间变化，提升控制任务的适应性与效率。
Time-Aware World Model for Adaptive Prediction and Control
- 根据时间步长Δt动态调整，学习不同频率的任务动态。
- 在多种控制任务中，相同训练量下性能超越传统模型。
- 适合需要高效适应不同采样率的强化学习场景。
本文提出时间感知世界模型（TAWM），一种显式建模时间动态的基于模型方法。通过将时间步长Δt作为条件输入，并在多样化的Δt值上进行训练（而非固定采样率），TAWM能够同时学习各类控制任务中的高频与低频动态。该设计基于信息论洞察：最优采样率取决于系统内在动态。实验表明，无论观察频率如何变化，TAWM均在多个控制任务中以相同训练样本和迭代次数优于传统模型，显著提升性能与数据效率。代码已公开于github.com/anh-nn01/Time-Aware-World-Model。
原文摘要 · Abstract (English)
In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Δt, and training over a diverse range of Δt values -- rather than sampling at a fixed time-step -- TAWM learns both high- and low-frequency task dynamics across diverse control problems. Grounded in the information-theoretic insight that the optimal sampling rate depends on a system's underlying dynamics, this time-aware formulation improves both performance and data efficiency. Empirical evaluations show that TAWM consistently outperforms conventional models across varying observation rates in a variety of control tasks, using the same number of training samples and iterations. Our code can be found online at: github.com/anh-nn01/Time-Aware-World-Model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。