EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Martingale Deep Reinforcement Learning for High-Dimensional Financial Problems

Hang Qi, Dingli Xia, Mingxiang Deng, Xiaofei Guan

Mathematics · 03.11.2026 · 14 (21) · 4012

DOI: 10.3390/math14214012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 03.11.2026. Verfasst von Hang Qi und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We develop a martingale-residual framework for continuous-time reinforcement learning in high-dimensional financial problems, linking policy evaluation (PE), policy gradient (PG), and entropy-regularized Actor–Critic (AC) learning. First, continuous-time PE and PG are often developed through separate constructions. We formulate a common martingale residual for the Critic and Actor, and show that, as the local time step vanishes, its rescaled policy derivative recovers the classical continuous-time PG. We also quantify how Critic approximation errors affect policy-gradient accuracy. Second, martingale-orthogonality temporal-difference (TD) methods require prescribed test functions, and their performance can depend on that choice. We introduce a weak-martingale adversarial formulation in which the test function is learned rather than prescribed. The resulting minimax problem avoids the sensitivity to hand-chosen test functions and provides a unified computational representation of the associated moment conditions. Third, direct high-dimensional Hamilton–Jacobi–Bellman (HJB) implementations can require explicit Hessians and other higher-order differential operators. Our algorithms work directly with sampled martingale residuals and first-order automatic differentiation, yielding Hessian-free implementations for both offline training from complete trajectories and online updating from sequential transitions. Numerical experiments on high-dimensional basket-option pricing and mean–variance portfolio selection demonstrate accurate PE and effective PG. In high-dimensional mean–variance portfolio-selection experiments, the proposed method achieves competitive or superior performance on several key metrics relative to benchmarks: the offline variant achieves a mean annualized return of 16.223%, the online variant attains a mean Sharpe ratio of 2.337, and fixed-budget training time increases by 19.3% as the asset dimension grows from 10 to 1000.

Zitieren

APA

Qi, H., Xia, D., Deng, M., & Guan, X. (2026). Martingale Deep Reinforcement Learning for High-Dimensional Financial Problems. Mathematics, 14(21), 4012. https://doi.org/10.3390/math14214012

Vancouver

Qi H, Xia D, Deng M, Guan X. Martingale Deep Reinforcement Learning for High-Dimensional Financial Problems. Mathematics. 2026;14(21):4012. doi:10.3390/math14214012

BibTeX
@article{Qi2026,
  author = {Qi, Hang and Xia, Dingli and Deng, Mingxiang and Guan, Xiaofei},
  title = {Martingale Deep Reinforcement Learning for High-Dimensional Financial Problems},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {21},
  pages = {4012},
  doi = {10.3390/math14214012}
}
Kostenlos starten →