FinRL-Podracer: High Performance and Scalable Deep Reinforcement Learning for Quantitative Finance.
Zechu LiXiao-Yang LiuJiahao ZhengZhaoran WangAnwar WalidJian GuoPublished in: CoRR (2021)
Keyphrases
- temporal difference learning
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- data intensive
- state space
- markov decision processes
- web scale
- model free
- machine learning
- computational intelligence
- low latency
- quantitative and qualitative
- highly scalable
- qualitative and quantitative
- data sets
- learning problems
- optimal policy
- dynamic programming
- reinforcement learning methods
- small sized
- robotic control