Batch Value-function Approximation with Only Realizability.
Tengyang XieNan JiangPublished in: ICML (2021)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- temporal difference learning
- monte carlo
- step size
- batch mode
- real time
- machine learning
- decision trees
- computer vision
- batch processing
- batch learning
- search algorithm
- basis functions
- image sequences
- online algorithms
- database
- batch size
- fermentation process