Model-Free Nonlinear Feedback Optimization.

Zhiyu He Saverio Bolognani Jianping He Florian Dörfler Xinping Guan

Published in: IEEE Trans. Autom. Control. (2024)

Keyphrases

model free
reinforcement learning
reinforcement learning algorithms
temporal difference
function approximation
policy iteration
constrained optimization
neural network
average reward
learning algorithm
learning process
small number