Provably Efficient Reinforcement Learning with Linear Function Approximation.
Chi JinZhuoran YangZhaoran WangMichael I. JordanPublished in: CoRR (2019)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- temporal difference learning
- learning tasks
- radial basis function
- mountain car
- reinforcement learning algorithms
- state action space
- tile coding
- model free
- temporal difference methods
- markov decision processes
- td learning
- least squares
- state space
- dynamic programming
- reinforcement learning methods
- continuous state
- pattern recognition