Login / Signup

Learning CPG-based biped locomotion with a policy gradient method.

Takamitsu MatsubaraJun MorimotoJun NakanishiMasa-aki SatoKenji Doya
Published in: Robotics Auton. Syst. (2006)
Keyphrases
  • gradient method
  • reinforcement learning
  • recommender systems
  • mobile robot
  • natural language processing
  • data clustering
  • humanoid robot