Online Sub-Sampling for Reinforcement Learning with General Function Approximation.
Dingwen KongRuslan SalakhutdinovRuosong WangLin F. YangPublished in: CoRR (2021)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- temporal difference learning
- state action space
- temporal difference learning algorithms
- radial basis function
- learning tasks
- tile coding
- mountain car
- model free
- reinforcement learning algorithms
- function approximators
- learning process
- td learning
- exploration exploitation tradeoff
- temporal difference methods
- machine learning
- policy gradient
- multi agent
- image classification
- supervised learning
- state space