Temporal Parallelisation of Dynamic Programming and Linear Quadratic Control.

Simo Särkkä Ángel F. García-Fernández

Published in: CoRR (2021)

Keyphrases

optimal control
linear quadratic
dynamic programming
vector valued
gaussian model
computer vision
closed loop
control system
state space
control method
real time
control strategy
bayesian networks
reinforcement learning
search space
dynamical systems