Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and Supervised Learning.
Tinghao ZhangZhijun LiYongrui ChenKwok-Yan LamJun ZhaoPublished in: iThings/GreenCom/CPSCom/SmartData/Cybermatics (2022)
Keyphrases
- reinforcement learning
- supervised learning
- multi agent
- cooperative
- temporal difference
- function approximation
- learning algorithm
- kernel based learning
- cloud computing
- reinforcement learning algorithms
- multi agent systems
- edge detection
- state space
- machine learning
- unsupervised learning
- optimal policy
- markov decision processes
- learning tasks
- bayesian inference
- learning problems
- bayesian networks
- model free
- edge information
- statistical learning
- neural network
- semi supervised learning
- function approximators
- training data
- optimal control
- probabilistic inference
- edge detector
- weighted graph
- action selection
- inference process
- data center
- robotic control
- unlabeled data