Reinforcement Learning for Biped Locomotion.
Masa-aki SatoYutaka NakamuraShin IshiiPublished in: ICANN (2002)
Keyphrases
- reinforcement learning
- robot control
- function approximation
- humanoid robot
- markov decision processes
- state space
- model free
- dynamic programming
- biped walking
- legged locomotion
- control strategy
- multi agent
- mobile robot
- optimal control
- optimal policy
- robotic systems
- reinforcement learning algorithms
- temporal difference learning
- robotic control
- data sets
- real time
- least squares
- control law
- learning classifier systems
- learning algorithm
- multi agent reinforcement learning
- legged robots