Adaptive overlay selection at the SD-WAN edges: A reinforcement learning approach with networked agents.
Alessio BottaRoberto CanonicoAnnalisa NavarroGiovanni StancoGiorgio VentrePublished in: Comput. Networks (2024)
Keyphrases
- reinforcement learning
- multi agent
- multi agent systems
- adaptive behavior
- learning capabilities
- learning agents
- action selection
- cooperative
- multi agent reinforcement learning
- multiple agents
- intelligent agents
- multi agent environments
- mobile agents
- autonomous agents
- reinforcement learning agents
- single agent
- machine learning
- multiagent learning
- agent receives
- dynamic environments
- function approximation
- learning agent
- agent architecture
- agent behavior
- partial observability
- resource allocation
- multiagent reinforcement learning
- state space
- incomplete information
- artificial agents
- software agents
- multimedia
- learning process
- evolutionary learning
- learned knowledge
- stochastic games
- edge detector
- temporal difference