Regular Ordering and Applications in Control Policies.

Eitan Altman Bruno Gaujal Arie Hordijk

Published in: Discret. Event Dyn. Syst. (2002)

Keyphrases

control policies
optimal policy
stochastic optimization problems
control policy
reinforcement learning
control system
control strategies
finite horizon
motion control
action space
search space
np hard
mobile robot
state space
bayesian networks
decision problems
finite number
machine learning
neural network