Learning and information in stochastic networks and queues
We review the role of information and learning in the stability and optimization of queueing
systems. In recent years, techniques from supervised learning, online learning, and …
systems. In recent years, techniques from supervised learning, online learning, and …
An online learning approach to dynamic pricing and capacity sizing in service systems
We study a dynamic pricing and capacity sizing problem in a GI/GI/1 queue, in which the
service provider's objective is to obtain the optimal service fee p and service capacity μ so as …
service provider's objective is to obtain the optimal service fee p and service capacity μ so as …
Bayesian learning of optimal policies in markov decision processes with countably infinite state-space
S Adler, V Subramanian - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Abstract Models of many real-life applications, such as queueing models of communication
networks or computing systems, have a countably infinite state-space. Algorithmic and …
networks or computing systems, have a countably infinite state-space. Algorithmic and …
Online learning and optimization for queues with unknown demand curve and service distribution
We investigate an optimization problem in a queueing system where the service provider
selects the optimal service fee p and service capacity\mu to maximize the cumulative …
selects the optimal service fee p and service capacity\mu to maximize the cumulative …
Learning to stabilize online reinforcement learning in unbounded state spaces
In many reinforcement learning (RL) applications, we want policies that reach desired states
and then keep the controlled system within an acceptable region around the desired states …
and then keep the controlled system within an acceptable region around the desired states …
QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
Queuing network control determines the allocation of scarce resources to manage
congestion, a fundamental problem in manufacturing, communications, and healthcare …
congestion, a fundamental problem in manufacturing, communications, and healthcare …
Differentiable Discrete Event Simulation for Queuing Network Control
Queuing network control is essential for managing congestion in job-processing systems
such as service systems, communication networks, and manufacturing processes. Despite …
such as service systems, communication networks, and manufacturing processes. Despite …
Toward the confident deployment of real‐world reinforcement learning agents
JP Hanna - AI Magazine, 2024 - Wiley Online Library
Intelligent learning agents must be able to learn from experience so as to accomplish tasks
that require more ability than could be initially programmed. Reinforcement learning (RL) …
that require more ability than could be initially programmed. Reinforcement learning (RL) …
Meta-scheduling for the wireless downlink through learning with bandit feedback
J Song, G De Veciana… - IEEE/ACM Transactions …, 2021 - ieeexplore.ieee.org
In this paper, we study learning-assisted multi-user scheduling for the wireless downlink.
There have been many scheduling algorithms developed that optimize for a plethora of …
There have been many scheduling algorithms developed that optimize for a plethora of …
Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem
SU Haque, ST Maguluri - arXiv preprint arXiv:2410.21704, 2024 - arxiv.org
Motivated by engineering applications such as resource allocation in networks and
inventory systems, we consider average-reward Reinforcement Learning with unbounded …
inventory systems, we consider average-reward Reinforcement Learning with unbounded …