Variance-Aware Off-Policy Evaluation with Linear Function Approximation.
Yifei MinTianhao WangDongruo ZhouQuanquan GuPublished in: CoRR (2021)
Keyphrases
- function approximation
- policy evaluation
- temporal difference
- reinforcement learning
- variance reduction
- td learning
- function approximators
- model free
- semi parametric
- learning tasks
- least squares
- reinforcement learning algorithms
- radial basis function
- monte carlo
- real valued
- statistical inference
- sufficient conditions
- cost function
- feature selection