Physics-Informed Learning for Multiplayer Differential Games
IEEE Control Systems Letters · 2026 · 10 · 619-624
DOI: 10.1109/lcsys.2026.3700693 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Control Systems Letters, 2026. Verfasst von Takuma Adams und 2 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Gefördert von: Commonwealth through an Australian Government Research Training Program Scholarship.
Abstract (Originalsprache)
Computing per-player feedback strategies in $N$ -player adversarial differential games is computationally challenging as the associated coupled Hamilton-Jacobi-Bellman system is high-dimensional and generally lacks classical solutions. We address this by approximating viscosity solutions using physics-informed neural networks within a policy iteration scheme with a vanishing-viscosity annealing schedule. Theoretically, we establish an explicit $\varepsilon $ -Nash guarantee by bounding per-player regret via computable residuals and prove our method reaches this stopping criterion in finite time. For two-player zero-sum games, we further establish a computable bound on approximation error for the value functions. Numerical experiments on pursuit-evasion scenarios illustrate the tightness of these computed bounds and the framework’s scalability to high-dimensional environments.
Förderung
- Commonwealth through an Australian Government Research Training Program Scholarship
Zitieren
APA
Adams, T., Cullen, A. C., & Alpcan, T. (2026). Physics-Informed Learning for Multiplayer Differential Games. IEEE Control Systems Letters, 10, 619-624. https://doi.org/10.1109/lcsys.2026.3700693
Vancouver
Adams T, Cullen AC, Alpcan T. Physics-Informed Learning for Multiplayer Differential Games. IEEE Control Systems Letters. 2026;10:619-624. doi:10.1109/lcsys.2026.3700693
BibTeX
@article{Adams2026,
author = {Adams, Takuma and Cullen, Andrew C. and Alpcan, Tansu},
title = {Physics-Informed Learning for Multiplayer Differential Games},
journal = {IEEE Control Systems Letters},
year = {2026},
volume = {10},
pages = {619--624},
doi = {10.1109/lcsys.2026.3700693}
}
EUVIMED