Invariant Adaptive Dynamic Programming for Discrete-Time Optimal Control.

Yuanheng Zhu Dongbin Zhao Haibo He

Published in: IEEE Trans. Syst. Man Cybern. Syst. (2020)

Keyphrases

optimal control
dynamic programming
optimal control problems
linear quadratic
control problems
infinite horizon
feedback control

state space
class of nonlinear systems
risk sensitive
control law
reinforcement learning
greedy algorithm

adaptive fuzzy
brownian motion
markov decision processes
multistage
actor critic
control strategy

adaptive control
average cost
policy gradient
markov chain
linear programming
real time