Bounds for approximate dynamic programming based on string optimization and curvature.

Yajing Liu Edwin K. P. Chong Ali Pezeshki William Moran

Published in: CDC (2014)

Keyphrases

approximate dynamic programming
linear program
dynamic programming
reinforcement learning
stochastic dynamic programming
upper bound
multiscale
control policy
least squares
global optimization
step size
optimal control
lower bound
factored mdps
optimization algorithm
subband
objective function
learning algorithm