Proximal Policy Optimization with Mixed Distributed Training.
Zhenyu ZhangXiangfeng LuoTong LiuShaorong XieJianshu WangWei WangYang LiYan PengPublished in: ICTAI (2019)
Keyphrases
- optimization algorithm
- optimization problems
- training set
- cooperative
- distributed systems
- multi agent
- stochastic gradient descent
- global optimization
- autonomy oriented computing
- computer networks
- distributed environment
- training samples
- supervised learning
- lightweight
- online learning
- optimization method
- training algorithm
- asymptotically optimal
- test set
- linear programming
- sensor networks
- distributed data
- multi objective
- distributed network
- learning algorithm