We have 3 of 57 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work develops a multi-agent reinforcement learning (MARL) algorithm, termed Multi-Agent Proximal Policy Optimization with Dirichlet Modeling (MAPPO-DM), which follows the centralized-training-and-decentralized-execution framework and models continuous traffic-splitting actions using a Dirichlet distribution.
A pinching-antenna system (PASS)-enabled multi-UAV integrated sensing and communication (ISAC) framework is proposed for adaptive downlink communications and UAV sensing. By jointly optimizing the pinching antenna (PA) activation, waveguide-level baseband precoding, and PA-level radiation power, the weighted sum of communication rates and sensing information rates is maximized, subject to the minimum-rate requirements of communication users (CUs) and sensing targets (STs). To address the resulting mixed-integer, high-dimensional, and strongly coupled non-convex problem, a genetic algorithm (GA)-based two-layer optimization (TLO) framework is developed. The PA activation is inferred by a GA-trained MLP policy in the outer layer, while the waveguide-level baseband precoding and PA-level radiation power are alternately optimized using weighted minimum mean-square error (WMMSE) and successive convex approximation (SCA) in the inner layer. Numerical results demonstrate that the proposed GA-TLO significantly improves both weighted sum rate and constraint satisfaction compared with conventional multiple-antenna architectures. Moreover, it achieves up to a 35% higher weighted sum rate than the fixed-activation PASS benchmark with BCD-based continuous optimization, while also substantially outperforming the fully uniform PASS and MIMO baselines.
A hierarchical joint optimization algorithm is developed within a multi-agent deep reinforcement learning (MADRL) framework to coordinate UAVs and MTs in a distributed manner and outperforms other benchmarks under varying network scales and capabilities by jointly optimizing UAV operations and resource utilization.
