Stochastic Policy Gradient Ascent in Reproducing Kernel Hilbert Spaces.
Santiago PaternainJuan Andrés BazerqueAustin SmallAlejandro RibeiroPublished in: IEEE Trans. Autom. Control. (2021)
Keyphrases
- reproducing kernel hilbert space
- policy gradient
- loss function
- kernel methods
- euclidean space
- special case
- optimal control
- reinforcement learning
- kernel function
- monte carlo
- input space
- density estimation
- neural network
- real valued
- gradient method
- distance measure
- gaussian process
- learning problems
- learning algorithm
- machine learning