On integral generalized policy iteration for continuous-time linear quadratic regulations.

Jae Young Lee Jin Bae Park Yoon Ho Choi

Published in: Autom. (2014)

Keyphrases

optimal control
policy iteration
linear quadratic
infinite horizon
dynamic programming
markov decision processes
control strategy
average reward
reinforcement learning
fixed point
dynamical systems
average cost
least squares
markov decision process
model free
optimal policy
state space
computer vision
finite state