Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle.
Simon S. DuYuping LuoRuosong WangHanrui ZhangPublished in: NeurIPS (2019)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- temporal difference learning
- radial basis function
- tile coding
- temporal difference
- learning tasks
- model free
- td learning
- temporal difference methods
- mountain car
- machine learning
- reinforcement learning algorithms
- function approximators
- supervised learning