Using Reinforcement Learning for Model-free Linear Quadratic Control with Process and Measurement Noises.

Farnaz Adib Yaghmaie Fredrik Gustafsson

Published in: CDC (2019)

Keyphrases

model free
reinforcement learning
optimal control
function approximation
reinforcement learning algorithms
linear quadratic
temporal difference
policy iteration
impedance control
control system
neural network
closed loop
model selection
training data
feature extraction
average reward
face recognition