A Reinforcement Learning based Edge Cloud Collaboration.
Hiroki KobariZhaoyang DuCelimuge WuTsutomu YoshinagaWugedele BaoPublished in: ICT-DM (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- cloud computing
- edge detection
- multi agent
- edge information
- edge detector
- markov decision processes
- reinforcement learning algorithms
- collaborative learning
- weighted graph
- multiple perspectives
- markov decision process
- machine learning
- policy search
- action selection
- multi agent reinforcement learning
- geographically dispersed
- model free
- data sets
- optimal control
- knowledge sharing
- information sharing
- transfer learning
- data management
- multi agent systems
- learning algorithm
- neural network