Multi-Agent Deep Reinforcement Learning for Cost- and Delay-Sensitive Virtual Network Function Placement and Routing.
Shaoyang WangChau YuenWei NiYong Liang GuanTiejun LvPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- network reliability
- routing decisions
- network topologies
- transmission delay
- link failure
- network model
- network communication
- multipath routing
- computer networks
- function approximation
- path length
- multicast tree
- packet switching
- function approximators
- network topology
- network congestion
- traffic load
- dynamic routing
- routing table
- bandwidth requirements
- network structure
- network layer
- network nodes
- communication cost
- wireless ad hoc networks
- learning agents
- learning algorithm
- multiple paths
- routing scheme
- destination node
- leader follower
- routing overhead
- wireless mesh networks
- single agent
- communication networks
- network traffic
- multi agent systems
- end to end delay
- wireless sensor networks
- state space
- response time
- packet delivery
- peer to peer
- shortest path
- markov decision processes
- end to end
- qos routing
- bandwidth consumption
- multi agent environments
- packet loss
- ip networks