Optimal Routing to Parallel Servers With Unknown Utilities - Multi-Armed Bandit With Queues.

Xinzhe Fu Eytan H. Modiano

Published in: IEEE/ACM Trans. Netw. (2023)

Keyphrases

multi armed bandit
multi armed bandits
service rates
optimal solution
reinforcement learning
queue length
arrival rate
service times
load balance
decision trees
worst case
graphical models
queueing networks
decentralized decision making