控制理论与应用2023,Vol.40Issue(10):1774-1782,9.DOI:10.7641/CTA.2022.20152
基于Bandit反馈的自适应量化分布式在线镜像下降算法
Adaptive quantized online distributed mirror descent algorithm with Bandit feedback
摘要
关键词
镜像下降算法/多智能体系统/优化/量化/Bandit反馈Key words
mirror descent algorithm/multi-agent systems/optimization/quantization/Bandit feedback引用本文复制引用
谢俊如,高文华,谢奕彬..基于Bandit反馈的自适应量化分布式在线镜像下降算法[J].控制理论与应用,2023,40(10):1774-1782,9.基金项目
国家自然科学基金项目(62273157),广州市科技计划项目(202002030158)资助.Supported by the National Natural Science Foundation of China(62273157)and the Guangzhou Science and Technology Planning Project(202002030158). (62273157)