Deep FPF: Gain function approximation in high-dimensional setting.
Sukru Yagiz OlmezAmirhossein TaghvaeiPrashant G. MehtaPublished in: CoRR (2020)
Keyphrases
- function approximation
- high dimensional
- reinforcement learning
- temporal difference
- temporal difference learning
- learning tasks
- temporal difference learning algorithms
- low dimensional
- radial basis function
- function approximators
- model free
- nearest neighbor
- dimensionality reduction
- high dimensional data
- td learning
- pattern recognition
- data sets
- exploration exploitation tradeoff
- mackey glass
- temporal difference methods
- data points
- feature space
- multi agent
- feature extraction
- machine learning