Understanding the Impact of Data Distribution on Q-learning with Function Approximation.
Pedro P. SantosFrancisco S. MeloAlberto SardinhaDiogo S. CarvalhoPublished in: CoRR (2021)
Keyphrases
- function approximation
- data distribution
- reinforcement learning
- tile coding
- temporal difference learning
- data streams
- radial basis function
- index structure
- model free
- learning tasks
- high dimensional data
- temporal difference
- temporal difference learning algorithms
- data points
- reinforcement learning algorithms
- td learning
- multi dimensional
- artificial neural networks
- multi agent
- temporal difference methods
- machine learning
- management system
- function approximators
- feature space
- reinforcement learning problems