An actor-critic reinforcement learning-based resource management in mobile edge computing systems.
Fang FuZhicai ZhangFei Richard YuQiao YanPublished in: Int. J. Mach. Learn. Cybern. (2020)
Keyphrases
- resource management
- computing systems
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- optimal control
- neuro fuzzy
- approximate dynamic programming
- reinforcement learning algorithms
- computer systems
- management system
- resource allocation
- gradient method
- function approximation
- policy iteration
- mobile devices
- quality of service
- intelligent agents
- model free
- state space
- grid computing
- context aware
- mobile users
- computing environments
- rl algorithms
- average reward
- learning algorithm
- real time
- resource manager
- mobile computing
- optimal policy
- data processing
- dynamic programming
- markov decision processes
- application developers
- multi agent
- decision making
- information systems
- machine learning
- action space
- function approximators
- case study
- data mining