Approximate dynamic programming for rail operations.

Warren B. Powell Belgacem Bouzaïene-Ayari

Published in: ATMOS (2007)

Keyphrases

approximate dynamic programming
linear program
reinforcement learning
dynamic programming
stochastic dynamic programming
high speed
step size
control policy
factored mdps
machine learning
average cost
decision making
lower bound
markov decision processes
optimal control
policy iteration