Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT.
Tingting FuYanjun PengPeng LiuHaksrun LaoShaohua WanPublished in: J. Cloud Comput. (2022)
Keyphrases
- reinforcement learning
- multi agent
- distributed systems
- industrial applications
- distributed environment
- computing environments
- markov decision processes
- function approximation
- cooperative
- sensor networks
- state space
- robotic control
- edge detection
- supervised learning
- optimal policy
- multiscale
- fault tolerant
- learning process
- location information
- edge information
- model free
- temporal difference