Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints.
Tianhao WangDongruo ZhouQuanquan GuPublished in: NeurIPS (2021)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference
- temporal difference learning
- learning tasks
- model free
- mountain car
- state action space
- tile coding
- feature selection
- radial basis function
- state space
- learning algorithm
- reinforcement learning problems
- temporal difference methods
- machine learning
- neural network
- fixed point
- semi supervised
- support vector machine
- reinforcement learning algorithms
- dynamic programming
- policy gradient
- pattern recognition
- multi agent