Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space.
Xiaoyuan ChengBoli ChenLiz VargaYukun HuPublished in: CoRR (2023)
Keyphrases
- reproducing kernel hilbert space
- reinforcement learning
- learning problems
- kernel methods
- euclidean space
- loss function
- density estimation
- learning theory
- kernel function
- domain adaptation
- special case
- gaussian process
- real valued
- high order
- data dependent
- distance measure
- vector valued
- input space
- kernel matrix
- machine learning
- supervised learning
- learning algorithm
- metric learning
- transfer learning
- dimensionality reduction
- pairwise
- feature space
- support vector
- positive definite