What are the Statistical Limits of Offline RL with Linear Function Approximation?
Ruosong WangDean P. FosterSham M. KakadePublished in: ICLR (2021)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- tile coding
- temporal difference learning
- model free
- temporal difference
- learning tasks
- radial basis function
- td learning
- reinforcement learning algorithms
- policy gradient
- learning algorithm
- temporal difference methods
- state space
- optimal control
- dynamic programming
- pattern recognition
- decision trees
- data mining
- exploration exploitation tradeoff