The impact of data distribution on Q-learning with function approximation.
Pedro P. SantosDiogo S. CarvalhoAlberto SardinhaFrancisco S. MeloPublished in: Mach. Learn. (2024)
Keyphrases
- function approximation
- data distribution
- reinforcement learning
- temporal difference learning
- tile coding
- learning tasks
- data streams
- index structure
- temporal difference
- model free
- temporal difference learning algorithms
- radial basis function
- high dimensional data
- td learning
- data points
- function approximators
- pattern recognition
- reinforcement learning algorithms
- neural network
- text categorization
- multi dimensional
- learning process
- image processing
- machine learning