lmcggg/Explicit-Discount-Method-for-LQR-controller
The primary goal of this algorithm is to learn a stabilizing feedback controller `K` for a linear time-invariant (LTI) system `x_{t+1} = Ax_t + Bu_t` **without prior knowledge of the system matrices `A` and `B`**, and without requiring an initial stabilizing policy.
正在读取项目信息…