Doubly coprime factorizations related to any stabilizing controllers in state space.

João Yoshiyuki Ishihara Roberto Moura Sales

Published in: Autom. (1999)

Keyphrases

state space
reinforcement learning
dynamic programming
optimal policy
heuristic search
nonlinear systems
closely related
real time
neural network
image sequences
expert systems
search space
control system
markov decision processes