Reinforcement learning for balancer embedded humanoid locomotion.
Akihiko YamaguchiSang-Ho HyonTsukasa OgasawaraPublished in: Humanoids (2010)
Keyphrases
- case study
- reinforcement learning
- degrees of freedom
- robot control
- function approximation
- state space
- learning algorithm
- reinforcement learning algorithms
- embedded systems
- neural network
- robotic systems
- database
- markov decision processes
- humanoid robot
- least squares
- mobile robot
- optimal policy
- optimal control
- information systems
- watermarking algorithm
- model free
- computer vision
- information retrieval
- policy search