Sign in
Using a controller based on reinforcement learning for a passive dynamic walking robot.
Erik Schuitema
Daan G. E. Hobbelen
Pieter P. Jonker
Martijn Wisse
J. G. Daniël Karssen
Published in:
Humanoids (2005)
Keyphrases
</>
reinforcement learning
walking robot
dynamic environments
optimal control
control system
machine learning
optimal policy
temporal difference
dynamic response
multi agent
evolutionary algorithm
state space
real time
numerical simulations
dynamic model
control theory
neural network