Deep FPF: Gain function approximation in high-dimensional setting.
Sukru Yagiz OlmezAmirhossein TaghvaeiPrashant G. MehtaPublished in: CDC (2020)
Keyphrases
- function approximation
- high dimensional
- reinforcement learning
- temporal difference learning algorithms
- temporal difference learning
- learning tasks
- radial basis function
- model free
- low dimensional
- temporal difference
- high dimensional data
- dimensionality reduction
- data points
- exploration exploitation tradeoff
- function approximators
- feature space
- neural network
- data sets
- kernel function
- small number