基于ASDDPG算法的多無人機對抗策略

打開文本圖片集

中圖分類號：TP181 文獻標(biāo)志碼：A DOI：10.12305/j.issn.1001-506X.2025.06.15

Abstract：Ina multi-unmanned aerial vehicle（UAV）confrontation，the number of friendly UAVs within therange of the UAVs communication is indeterminate，resulting in changes in the amount of information it obtains.In deep reinforcement learning，the input dimension of the neural network is fixed，and many algorithmsonlyconsider theinteraction informationofa fixed numberof friendly UAVsatarelativelyclose distance，resulting in information lossand inconsistent with theactual battlefieldenvironment.In this regard， based on the multi-agent deep deterministic policy gradient （MADDPG） algorithm and attention mechanism，the atention state-deep deterministic policy gradient（ASDDPG）algorithm is proposed to transform changing information into fixed-length feature vectors，which solves the problem of mismatch between amount of information and input dimension，and extracts state features through coder and decoder structure to enhance the decision-makingabilityof UAVs.Simulation experimentsaredesigned tocompare andanalyze theperformanceof the proposed algorithm，and verifythe performance advantageofthe proposed algorithm withabetter wining probability. Thealgorithm’sadvantages in improving UAVsadversarial decision-making and generalization have been verified in this study.

Keywords：multi-unmanned aerial vehicle（UAV）；reinforcement learning；policy gradient；maneuver decision-making，attention mechanism

0 引言

為在現(xiàn)代戰(zhàn)爭中發(fā)揮著重要作用[2-3]。（剩余23754字）