Learning to Adapt: Reptile-D-Learning for Robust and Efficient Control Under Parametric Uncertainty
学会适应:面向参数不确定性的鲁棒高效控制的Reptile-D-Learning
机构 * School of Automation Science and Electrical Engineering, Beihang University(北京航空航天大学自动化科学与电气工程学院)
AI总结 提出Reptile-D-learning框架,结合元学习算法Reptile与D-learning,学习可泛化的Lyapunov网络初始化和高性能控制器,以应对参数不确定性,提升非线性控制系统的泛化与快速适应能力。