A Reinforcement Learning Approach for Interdomain Routing with Link Prices.
Peter VrancxPasquale GurziAbdel RodríguezKris SteenhautAnn NowéPublished in: ACM Trans. Auton. Adapt. Syst. (2015)
Keyphrases
- reinforcement learning
- link failure
- function approximation
- learning process
- routing problem
- reinforcement learning algorithms
- routing protocol
- routing algorithm
- robotic control
- dynamic pricing
- state space
- learning algorithm
- wireless ad hoc networks
- market data
- markov decision processes
- network topology
- optimal policy
- model free
- action selection
- temporal difference
- multi agent
- inter domain
- destination node
- optimal control
- routing table
- machine learning