Time-Aware World Model for Adaptive Prediction and Control
This work addresses adaptive prediction and control for robotics or simulation systems, offering an incremental improvement by enhancing data efficiency and performance over conventional models.
The paper tackles the problem of improving model-based control by incorporating temporal dynamics, introducing the Time-Aware World Model (TAWM) that conditions on time-step size and trains over diverse Δt values, resulting in consistent performance gains across varying observation rates in control tasks.
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.