Region-based approximation in approximate dynamic programming.

Tohid Sardarmehni Xingyong Song

Published in: Int. J. Control (2024)

Keyphrases

approximate dynamic programming
linear program
dynamic programming
reinforcement learning
stochastic dynamic programming
step size
image segmentation
factored mdps
linear programming
machine learning
control policy
optimal policy
average cost
queueing networks
multiscale
learning algorithm
genetic algorithm