Reinforcement Learning in Reproducing Kernel Hilbert Spaces: Enabling Continuous Brain?Machine Interface Adaptation.
Yiwen WangJosé C. PríncipePublished in: IEEE Signal Process. Mag. (2021)
Keyphrases
- reproducing kernel hilbert space
- reinforcement learning
- learning problems
- reproducing kernel
- loss function
- kernel methods
- gaussian kernels
- uniform convergence
- learning theory
- special case
- euclidean space
- covering numbers
- kernel function
- real valued
- gaussian process
- data dependent
- learning tasks
- learning rate
- similarity measure
- representer theorem
- learning process
- vc dimension
- domain adaptation
- distance measure
- sufficient conditions