Approximate Dynamic Programming for Generation of Robustly Stable Feedback Controllers.

Jakob Björnberg Moritz Diehl

Published in: HPSC (2006)

Keyphrases

cost function
approximate dynamic programming
step size
reinforcement learning
linear program
stochastic dynamic programming
dynamic programming
control system
particle swarm optimization
factored mdps
np hard
state space
mathematical model
control strategy
optimal control
control policy