State-space solution of the discrete-time minimum entropy control problem via separation.

Pablo A. Iglesias Denis Mustafa

Published in: IEEE Trans. Autom. Control. (1993)

Keyphrases

state space
reinforcement learning
markov chain
dynamic programming
dynamical systems
control theory
control method
control system
heuristic search
markov decision processes
solution quality
control problems
optimal solution
mathematical model
neural network
control strategy
linear equations
control policy