Scalable Reinforcement Learning for Dynamic Overlay Selection in SD-WANs.
Alessio BottaRoberto CanonicoAnnalisa NavarroGiovanni StancoGiorgio VentrePublished in: IFIP Networking (2023)
Keyphrases
- reinforcement learning
- dynamic environments
- dynamic programming
- function approximation
- neural network
- learning algorithm
- dynamically changing
- state space
- dynamically select
- selection criteria
- reinforcement learning algorithms
- selection strategy
- evaluation function
- learning process
- learning environment
- feature selection
- machine learning
- real world