Policy Iteration Algorithm for Constrained Cost Optimal Control of Discrete-Time Nonlinear System.

Tao Li Qinglai Wei Hongyang Li Ruizhuo Song

Published in: IJCNN (2021)

Keyphrases

optimal control
policy iteration algorithm
finite state
optimal control problems
average cost
infinite horizon
linear quadratic
policy iteration
markov chain
reinforcement learning
control problems
actor critic
dynamic programming
control strategy
feedback control
total cost
control law
machine learning