Gaussian Process Temporal-Difference Learning with Scalability and Worst-Case Performance Guarantees.
Qin LuGeorgios B. GiannakisPublished in: ICASSP (2021)
Keyphrases
- gaussian process
- temporal difference learning
- worst case
- hyperparameters
- regression model
- bayesian framework
- lower bound
- latent variables
- semi supervised
- upper bound
- model selection
- function approximation
- np hard
- fixed point
- sample size
- evaluation function
- closed form
- reinforcement learning
- learning algorithm
- higher order
- active learning
- temporal difference