Learning Throttle Valve Control Using Policy Search.

Bastian Bischoff Duy Nguyen-Tuong Torsten Koller Heiner Markert Alois C. Knoll

Published in: ECML/PKDD (1) (2013)

Keyphrases

policy search
reinforcement learning
learning algorithm
learning tasks
control system
learning problems
neural network
machine learning
computational complexity
mobile robot
hidden variables
action selection
robot control
motion control