Hybrid Reinforcement Learning and Its Application to Biped Robot Control.

Satoshi Yamada Akira Watanabe Michio Nakashima

Published in: NIPS (1997)

Keyphrases

robot control
reinforcement learning
mobile robot
object manipulation
autonomous robots
unstructured environments
motion control
model free
cerebellar model articulation controller
computer vision
motor control
biped robot
dynamic model
subsumption architecture
control strategy