Decentralized Task Offloading in Edge Computing: An Offline-to-Online Reinforcement Learning Approach.
Hongcai LinLei YangHao GuoJiannong CaoPublished in: IEEE Trans. Computers (2024)
Keyphrases
- reinforcement learning
- online learning
- multi agent
- real time
- cooperative
- balancing exploration and exploitation
- edge detection
- machine learning
- peer to peer
- function approximation
- model free
- optimal control
- robotic control
- policy search
- multi agent reinforcement learning
- online environment
- batch mode
- reinforcement learning algorithms
- undirected graph
- edge information
- markov decision processes
- data sets