Skip to main navigation Skip to search Skip to main content

EC-HSRA: Environment-Conditioned Hierarchical Shared-Resource Allocation for Multi-Task Regional Support

  • Jingxiang Ma
  • , Malak Abid Ali Khan
  • , Hongbin Ma*
  • , Youzhi Zhang
  • *Corresponding author for this work
  • Beijing Institute of Technology
  • Centre for Artificial Intelligence and Robotics
  • Chinese Academy of Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Regional support and emergency scheduling require repeated allocation of scarce defense, repair, mobility-assurance, and reconnaissance resources across responsibility regions under changing conditions. A shared-budget decision may prioritize a relevant task while failing to cover task-specific regions, or allocate resources to salient regions under an inappropriate task. Fixed sharing, pressure gating, and direct high-dimensional policies can ensure budget feasibility, yet they do not explicitly couple task allocation with task-conditioned regional decoding. This paper proposes Environment-Conditioned Hierarchical Shared-Resource Allocation (EC-HSRA). EC-HSRA abstracts the operating area as a regional graph and uses a constrained hierarchical action: the task layer learns state-conditioned task-budget allocation, and the regional layer generates task-specific threshold, focus, and coverage-mixing parameters. In the situation-cascade scenario, EC-HSRA reaches a mean shifted cumulative utility of 17.425, exceeding Pressure Gate at 10.972, Top-k Stitch at 14.522, and the explicit-prior variant at 16.524. Its normalized service-shortfall index is 0.941, lower than Pressure Gate at 1.047 and Unified Joint at 1.147. The results indicate that task-level allocation and task-specific regional decoding are complementary.

Original languageEnglish
Title of host publication2026 8th International Conference on Electronic Engineering and Informatics, EEI 2026
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages172-176
Number of pages5
ISBN (Electronic)9798331583682
DOIs
Publication statusPublished - 2026
Externally publishedYes
Event8th International Conference on Electronic Engineering and Informatics, EEI 2026 - Jinan, China
Duration: 26 Jun 2026 → 28 Jun 2026

Publication series

Name2026 8th International Conference on Electronic Engineering and Informatics, EEI 2026

Conference

Conference8th International Conference on Electronic Engineering and Informatics, EEI 2026
Country/TerritoryChina
CityJinan
Period26/06/26 → 28/06/26

Keywords

  • hierarchical reinforcement learning
  • multi-task regional support
  • regional allocation
  • shared-resource allocation
  • task-region mismatch

Fingerprint

Dive into the research topics of 'EC-HSRA: Environment-Conditioned Hierarchical Shared-Resource Allocation for Multi-Task Regional Support'. Together they form a unique fingerprint.

Cite this