ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning.
Xiao-Yang LiuZechu LiZhuoran YangJiahao ZhengZhaoran WangAnwar WalidJian GuoMichael I. JordanPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- cloud computing
- markov decision processes
- learning algorithm
- function approximation
- state space
- learning process
- multi agent
- map reduce
- machine learning
- optimal control
- highly scalable
- model free
- dynamic programming
- optimal policy
- deep learning
- policy search
- virtual machine
- dynamical systems
- transfer learning
- case study