On the Global Optimality of Direct Policy Search for Nonsmooth $\mathcal{H}_{\infty}$ Output-Feedback Control.
Yujie TangYang ZhengPublished in: CDC (2023)
Keyphrases
- feedback control
- direct policy search
- global optimality
- closed loop
- globally optimal
- optimal control
- adaptive control
- convex functions
- reinforcement learning
- global optimization
- optimal solution
- inverted pendulum
- theoretical guarantees
- objective function
- discrete optimization
- global minimum
- neural network
- finite number
- control method
- nonlinear systems
- global solution
- gradient field
- convex programming