A New Optimal Stepsize for Approximate Dynamic Programming.

Ilya O. Ryzhov Peter I. Frazier Warren B. Powell

Published in: IEEE Trans. Autom. Control. (2015)

Keyphrases

approximate dynamic programming
stochastic dynamic programming
step size
dynamic programming
linear program
reinforcement learning
control policy
average cost
linear programming
cost function
policy iteration
optimal solution
optimal policy
multistage
special case
optimal control
long run
evolutionary algorithm