Drift Plus Optimistic Penalty: A Learning Framework for Stochastic Network Optimization with Improved Regret Bounds

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chadaga, Sathwik, Modiano, Eytan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911248475488256
author Chadaga, Sathwik
Modiano, Eytan
author_facet Chadaga, Sathwik
Modiano, Eytan
contents We consider the problem of joint routing and scheduling in queueing networks, where the edge transmission costs are unknown. At each time-slot, the network controller receives noisy observations of transmission costs only for those edges it selects for transmission. The network controller's objective is to make routing and scheduling decisions so that the total expected cost is minimized. This problem exhibits an exploration-exploitation trade-off, however, previous bandit-style solutions cannot be directly applied to this problem due to the queueing dynamics. In order to ensure network stability, the network controller needs to optimize throughput and cost simultaneously. We show that the best achievable cost is lower bounded by the solution to a static optimization problem, and develop a network control policy using techniques from Lyapunov drift-plus-penalty optimization and multi-arm bandits. We show that the policy achieves a sub-linear regret of order $O(\sqrt{T}\log T)$, as compared to the best policy that has complete knowledge of arrivals and costs. Finally, we evaluate the proposed policy using simulations and show that its regret is indeed sub-linear.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Drift Plus Optimistic Penalty: A Learning Framework for Stochastic Network Optimization with Improved Regret Bounds
Chadaga, Sathwik
Modiano, Eytan
Networking and Internet Architecture
Systems and Control
We consider the problem of joint routing and scheduling in queueing networks, where the edge transmission costs are unknown. At each time-slot, the network controller receives noisy observations of transmission costs only for those edges it selects for transmission. The network controller's objective is to make routing and scheduling decisions so that the total expected cost is minimized. This problem exhibits an exploration-exploitation trade-off, however, previous bandit-style solutions cannot be directly applied to this problem due to the queueing dynamics. In order to ensure network stability, the network controller needs to optimize throughput and cost simultaneously. We show that the best achievable cost is lower bounded by the solution to a static optimization problem, and develop a network control policy using techniques from Lyapunov drift-plus-penalty optimization and multi-arm bandits. We show that the policy achieves a sub-linear regret of order $O(\sqrt{T}\log T)$, as compared to the best policy that has complete knowledge of arrivals and costs. Finally, we evaluate the proposed policy using simulations and show that its regret is indeed sub-linear.
title Drift Plus Optimistic Penalty: A Learning Framework for Stochastic Network Optimization with Improved Regret Bounds
topic Networking and Internet Architecture
Systems and Control
url https://arxiv.org/abs/2509.03762