Deep Reinforcement Learning Based Dynamic Resource Allocation in Cloud Radio Access Networks.
Rehenuma Tasnim RodoshiTaewoon KimWooyeol ChoiPublished in: ICTC (2020)
Keyphrases
- dynamic resource allocation
- reinforcement learning
- resource allocation
- cloud computing
- function approximation
- state space
- wireless communication
- machine learning
- reinforcement learning algorithms
- markov decision processes
- robotic control
- action selection
- model free
- allocation policies
- databases
- temporal difference
- optimal control
- virtual machine
- wifi
- temporal difference learning
- learning classifier systems
- computer simulation
- partially observable
- robot control
- deep learning
- radio frequency
- stochastic approximation
- multi agent reinforcement learning
- learning process
- multi agent
- learning algorithm