Asymptotic Optimal Control of Markov-Modulated Restless Bandits.

Santiago Duran Ina Maria Verloop

Published in: Proc. ACM Meas. Anal. Comput. Syst. (2018)

Keyphrases

optimal control
markov modulated
poisson process
dynamic programming
control strategy
control problems
reinforcement learning
stochastic systems
asymptotically optimal
arrival process
infinite horizon
large deviations
optimal control problems
arrival rate
real time
average cost
lower bound