Accelerated point-wise maximum approach to approximate dynamic programming.

Paul N. Beuchat Joseph Warrington John Lygeros

Published in: CoRR (2019)

Keyphrases

approximate dynamic programming
pointwise
linear program
weighted sum
stochastic dynamic programming
dynamic programming
reinforcement learning
step size
linear programming
average cost
control policy
confidence intervals
roc curve
policy iteration
cost function
optimal solution
objective function