Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation.
Jiafan HeDongruo ZhouQuanquan GuPublished in: NeurIPS (2021)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- upper bound
- temporal difference
- temporal difference learning
- model free
- mountain car
- vc dimension
- radial basis function
- learning tasks
- learning algorithm
- reinforcement learning algorithms
- state space
- actor critic
- optimal policy
- reinforcement learning problems
- feature extraction
- temporal difference methods
- step size
- image classification
- pattern recognition
- policy search
- machine learning