Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning.
Shuo YuHongyan XueXiang AoFeiyang PanJia HeDandan TuQing HePublished in: KDD (2023)
Keyphrases
- reinforcement learning
- function approximation
- information retrieval
- temporal difference
- state space
- model free
- learning algorithm
- metadata
- multi agent
- document collections
- robotic control
- machine learning
- autonomous learning
- partially observable
- dynamic programming
- query processing
- learning process
- digital libraries