Reinforcement Learning with Experience Replay for Model-Free Humanoid Walking Optimization.
Pawel WawrzynskiPublished in: Int. J. Humanoid Robotics (2014)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- humanoid robot
- temporal difference
- policy iteration
- rl algorithms
- state space
- temporal difference learning
- policy evaluation
- reinforcement learning methods
- motion planning
- degrees of freedom
- markov decision processes
- average reward
- optimal policy
- machine learning algorithms
- support vector
- learning algorithm
- machine learning