Decision-Making and Parameter Optimization of Anti-Jamming Measures based on HPPO

Jiaxiang Zhang, Siyuan Cai, Weiran Wang, Zhennan Liang*, Quanhua Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In the current dynamic jamming scenarios where radar faces diverse types and varying parameters of interference, it often requires simultaneous decision-making on a limited number of anti-jamming measures and their corresponding continuous parameters. To address this mixed action space optimization problem, this paper proposes a method for anti-jamming measure decision-making and parameter optimization based on the Hybrid Proximal Policy Optimization (HPPO) algorithm. Building on the PPO algorithm, the single output layer of the actor network is modified into two independent parallel output layers, each independently calculating the importance sampling values for measures and parameters, followed by policy updates using a shared advantage function. Simulations verify the effectiveness of the proposed algorithm.

Original languageEnglish
Title of host publicationIEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331515669
DOIs
Publication statusPublished - 2024
Event2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 - Zhuhai, China
Duration: 22 Nov 202424 Nov 2024

Publication series

NameIEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

Conference

Conference2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
Country/TerritoryChina
CityZhuhai
Period22/11/2424/11/24

Keywords

  • HPPO
  • measure decision-making
  • mixed action space
  • parameter optimization
  • radar anti-jamming

Fingerprint

Dive into the research topics of 'Decision-Making and Parameter Optimization of Anti-Jamming Measures based on HPPO'. Together they form a unique fingerprint.

Cite this