A Competitive Strategy for Function Approximation in Q-Learning.
Alejandro AgostiniEnric CelayaPublished in: IJCAI (2011)
Keyphrases
- function approximation
- reinforcement learning
- tile coding
- model free
- learning tasks
- temporal difference learning
- temporal difference learning algorithms
- radial basis function
- temporal difference
- state action space
- td learning
- reinforcement learning algorithms
- function approximators
- temporal difference methods
- mountain car
- text classification
- pattern recognition