An analysis of reinforcement learning with function approximation.
Francisco S. MeloSean P. MeynM. Isabel RibeiroPublished in: ICML (2008)
Keyphrases
- function approximation
- reinforcement learning
- model free
- temporal difference learning
- state action space
- temporal difference
- radial basis function
- tile coding
- function approximators
- learning tasks
- temporal difference learning algorithms
- td learning
- reinforcement learning algorithms
- supervised learning
- state space
- dynamic programming
- artificial neural networks
- training data
- feature selection
- genetic algorithm
- machine learning