Provably efficient reinforcement learning with linear function approximation.
Chi JinZhuoran YangZhaoran WangMichael I. JordanPublished in: COLT (2020)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- temporal difference learning
- tile coding
- model free
- mountain car
- radial basis function
- reinforcement learning algorithms
- state action space
- supervised learning
- learning tasks
- multi agent
- neural network
- dynamic programming
- kernel methods
- reinforcement learning problems