Time-Aware World Model for Adaptive Prediction and Control

Anh N Nhu, Sanghyun Son, Ming Lin
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46265-46287, 2025.

Abstract

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, $\Delta t$, and training over a diverse range of $\Delta t$ 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-nhu25a, title = {Time-Aware World Model for Adaptive Prediction and Control}, author = {Nhu, Anh N and Son, Sanghyun and Lin, Ming}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {46265--46287}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/nhu25a/nhu25a.pdf}, url = {https://proceedings.mlr.press/v267/nhu25a.html}, abstract = {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, $\Delta t$, and training over a diverse range of $\Delta t$ 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.} }
Endnote
%0 Conference Paper %T Time-Aware World Model for Adaptive Prediction and Control %A Anh N Nhu %A Sanghyun Son %A Ming Lin %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-nhu25a %I PMLR %P 46265--46287 %U https://proceedings.mlr.press/v267/nhu25a.html %V 267 %X 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, $\Delta t$, and training over a diverse range of $\Delta t$ 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.
APA
Nhu, A.N., Son, S. & Lin, M.. (2025). Time-Aware World Model for Adaptive Prediction and Control. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:46265-46287 Available from https://proceedings.mlr.press/v267/nhu25a.html.

Related Material