wanxinjin/Pontryagin-Differentiable-Programming

A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.

语言：Python · GitHub 星标：190 · Fork：25

话题：control-learning · control-systems · differentiable-programming · dynamical-systems · end-to-end-learning · imitation-learning · inverse-reinforcement-learning · learning-control

在 GitHub 上查看原仓库