EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

Adaptive Hierarchical RL for Dynamic Workload Management in Programmatic Advertising

Vincent Rossi, Min-Jae Park

Frontiers in Artificial Intelligence Research · 2025-09-19 · 2 (3) · 333-344

DOI: 10.71465/fair356 ↗

At a glance

Journal article in Frontiers in Artificial Intelligence Research, published online on 2025-09-19. Written by Vincent Rossi and 1 co-authors. The full text is freely available (open access, CC BY-NC-ND 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Dynamic workload management in programmatic advertising environments presents complex multi-objective optimization challenges that conventional Reinforcement Learning (RL) approaches struggle to address effectively. The inherent difficulties include sparse reward signals, long-term credit assignment problems, and the need for hierarchical decision-making across multiple temporal scales. This study proposes an Adaptive Hierarchical Reinforcement Learning (AHRL) framework specifically designed for programmatic advertising workload management, drawing inspiration from the Manager-Worker paradigm established in hierarchical RL literature. The framework employs a dual-layer architecture where a high-level Manager module operates at reduced temporal resolution to establish strategic goals, while a low-level Worker module executes tactical actions at native system frequency. Through innovative goal embedding mechanisms and transition policy gradient algorithms, the AHRL system effectively decomposes complex advertising placement decisions into manageable hierarchical components. Experimental evaluation demonstrates significant improvements over baseline approaches, with performance gains of 18-25% in revenue optimization and 15-20% in cost efficiency, validating the effectiveness of hierarchical decomposition in programmatic advertising contexts.

Cite

APA

Rossi, V., & Park, M. (2025). Adaptive Hierarchical RL for Dynamic Workload Management in Programmatic Advertising. Frontiers in Artificial Intelligence Research, 2(3), 333-344. https://doi.org/10.71465/fair356

Vancouver

Rossi V, Park M. Adaptive Hierarchical RL for Dynamic Workload Management in Programmatic Advertising. Frontiers in Artificial Intelligence Research. 2025;2(3):333-344. doi:10.71465/fair356

BibTeX
@article{Rossi2025,
  author = {Rossi, Vincent and Park, Min-Jae},
  title = {Adaptive Hierarchical RL for Dynamic Workload Management in Programmatic Advertising},
  journal = {Frontiers in Artificial Intelligence Research},
  year = {2025},
  volume = {2},
  number = {3},
  pages = {333--344},
  doi = {10.71465/fair356}
}
Start for free →