Finite-Sample Analysis for SARSA with Linear Function Approximation.
Shaofeng ZouTengyu XuYingbin LiangPublished in: NeurIPS (2019)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- temporal difference learning
- finite sample
- data sets
- sample size
- error bounds
- feature extraction
- pattern recognition
- learning tasks
- radial basis function
- reinforcement learning algorithms