Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces.
Stefan ElfwingEiji UchibeKenji DoyaPublished in: Frontiers Neurorobotics (2013)
Keyphrases
- efficient learning
- reinforcement learning
- state space
- high dimensional
- reinforcement learning algorithms
- markov decision processes
- learning algorithm
- function approximation
- structured prediction
- markov chain
- optimal policy
- machine learning
- action space
- pattern languages
- state abstraction
- log linear models
- high dimensional data
- low dimensional
- dimensionality reduction
- software engineering
- learning process