Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning.
Shuo YuHongyan XueXiang AoFeiyang PanJia HeDandan TuQing HePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- markov decision processes
- metadata
- information retrieval
- document collections
- reinforcement learning algorithms
- learning algorithm
- data collections
- optimal policy
- real robot
- generation process
- temporal difference learning
- robot control
- automatically generating
- data sets
- action selection
- active learning
- multi agent
- decision trees
- social networks
- data mining