Login / Signup
Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller.
Abbas Abdolmaleki
Nuno Lau
Luís Paulo Reis
Jan Peters
Gerhard Neumann
Published in:
J. Intell. Robotic Syst. (2016)
Keyphrases
</>
policy search
humanoid robot
reinforcement learning
continuous state
central pattern generator
optimal control
continuous action
reinforcement learning algorithms
neural network
dynamic programming
control system
control algorithm
mobile robot
state space
closed loop
partially observable markov decision processes