Reinforcement learning combined with human feedback in continuous state and action spaces.
Ngo Anh VienWolfgang ErtelPublished in: ICDL-EPIROB (2012)
Keyphrases
- continuous state and action spaces
- reinforcement learning
- continuous state
- action selection
- function approximation
- function approximators
- reinforcement learning algorithms
- machine learning
- supervised learning
- neural network
- learning algorithm
- multi agent
- dynamic programming
- state space
- markov decision processes
- temporal difference