Online Model Selection for Reinforcement Learning with Function Approximation.
Jonathan N. LeeAldo PacchianoVidya MuthukumarWeihao KongEmma BrunskillPublished in: CoRR (2020)
Keyphrases
- function approximation
- model selection
- reinforcement learning
- cross validation
- temporal difference learning
- function approximators
- temporal difference
- machine learning
- regression model
- model free
- sample size
- radial basis function
- feature selection
- model selection criteria
- reinforcement learning algorithms
- gaussian process
- selection criterion
- learning tasks
- unsupervised learning
- state space
- dynamic programming
- statistical inference
- optimal policy
- feature vectors
- artificial neural networks
- td learning
- objective function
- reinforcement learning problems
- training data
- exploration exploitation tradeoff