A Multiobjective Antenna Optimization Method Based on the Surrogate Model-Assisted Deep Reinforcement Learning

A novel multi-objective antenna optimization method based on the surrogate model-assisted deep reinforcement learning (SADRL) is proposed. The method is divided into three stages: coarse topology optimization, surrogate model construction, and fine topology optimization. First, the adaptive variable fidelity electromagnetic (AVFEM) model is used to assist the improved binary particle swarm optimization (IBPSO) algorithm for coarse optimization of antenna topology. This stage provides an initial database for surrogate-model training and a high-quality initial solution for subsequent deep reinforcement learning (DRL) algorithm. Second, the Bayesian Convolutional Neural Networks (BCNN) is employed as an online surrogate model, aiming to provide a low-cost interactive environment for the DRL. Finally, the deep Q-network (DQN) is used to perform fine optimization of antenna topology. To validate the proposed method, a multi-objective optimization of a monopole antenna is conducted with objectives of omnidirectionality, operating bandwidth, and in‑band gain flatness. The optimized design provides an operating band that covers 3.3–3.8 GHz and 5.75–5.85 GHz, while maintaining realized gains of 1.89 ± 0.23 dBi and 1.35 ± 0.11 dBi across the target bands, the azimuthal gain ripple is less than 2.86 dBi. Compared with other optimization methods, the proposed SADRL achieves the target design with fewer electromagnetic (EM) simulations.