Stochastic Policy Gradient Ascent in Reproducing Kernel Hilbert Spaces.
Santiago PaternainJuan Andrés BazerqueAustin SmallAlejandro RibeiroPublished in: CoRR (2018)
Keyphrases
- reproducing kernel hilbert space
- policy gradient
- kernel methods
- loss function
- special case
- euclidean space
- reinforcement learning
- kernel function
- density estimation
- gaussian process
- gradient method
- optimal control
- learning problems
- machine learning
- real valued
- monte carlo
- input space
- distance measure
- neural network
- similarity measure
- support vector machine