Proximal Policy Optimization with Mixed Distributed Training.
Zhenyu ZhangXiangfeng LuoShaorong XieJianshu WangWei WangYang LiPublished in: CoRR (2019)
Keyphrases
- distributed environment
- optimization algorithm
- distributed systems
- training phase
- optimization method
- training algorithm
- optimization process
- training set
- online learning
- fault tolerant
- optimal policy
- global optimization
- test set
- lightweight
- cooperative
- stochastic gradient descent
- genetic algorithm
- constrained optimization
- training process
- computer networks
- multi agent