Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic Regulator.

Feiran Zhao Keyou You

Published in: CoRR (2020)

Keyphrases

model free
primal dual
reinforcement learning
learning algorithm
linear quadratic
active learning
learning tasks
learning problems
convergence rate
convex optimization
function approximation
optimal control
least squares
linear programming
closed loop
multiresolution
saddle point
neural network