Adaptive Routing with Guaranteed Delay Bounds using Safe Reinforcement Learning.
Gautham Nayak SeetanadiKarl-Erik ÅrzénMartina MaggioPublished in: RTNS (2020)
Keyphrases
- reinforcement learning
- qos routing
- function approximation
- lower bound
- learning capabilities
- network topology
- upper and lower bounds
- upper bound
- supervised learning
- worst case
- shortest path
- lower and upper bounds
- monte carlo
- multi agent
- routing protocol
- markov decision processes
- dynamic routing
- end to end delay
- network reliability
- transmission delay
- qos parameters
- neural network
- routing algorithm
- steady state
- optimal policy
- dynamic programming
- learning process
- machine learning