Performance of Lookahead Control Policies in the Face of Abstractions and Approximations.

Ilya Levner Vadim Bulitko Omid Madani Russell Greiner

Published in: SARA (2002)

Keyphrases

control policies
optimal policy
stochastic optimization problems
control strategies
control policy
reinforcement learning
control system
motion control
finite horizon
action space
data mining
search algorithm