Queueing Network Controls via Deep Reinforcement Learning

DOI10.1287/stsy.2021.0081zbMath1489.60145arXiv2008.01644OpenAlexW3047127288MaRDI QIDQ5084497

No author found.

Publication date: 24 June 2022

Published in: Stochastic Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.01644

zbMATH Keywords

long-run average costreinforcement learningmulticlass queueing networkcontrol variate

Mathematics Subject Classification ID

Stochastic network models in operations research (90B15) Queueing theory (aspects of probability theory) (60K25) Queues and service in operations research (90B22)

Uses Software

• TensorFlow
• Adam
• Ray

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximate linear programming for networks: average cost bounds
• An online actor-critic algorithm with function approximation for constrained Markov decision processes
• State space collapse with application to heavy traffic limits for multiclass queueing networks
• Heavy traffic analysis of a system with parallel servers: Asymptotic optimality of discrete-review policies
• Optimization of multiclass queueing networks: Polyhedral and nonlinear characterizations of achievable performance
• Convergence to equilibria for fluid models of head-of-the-line proportional processor sharing queueing networks
• Brownian models of open processing networks: Canonical representation of workload.
• Heavy traffic analysis of open processing networks with complete resource pooling: asymptotic optimality of discrete review policies
• Brownian models of multiclass queueing networks: Current status and open problems
• Re-entrant lines
• Value iteration and optimization of multiclass queueing networks
• Batch size effects on the efficiency of control variates in simulation
• Performance evaluation and policy selection in multiclass networks
• Dynamic scheduling of a system with two parallel servers in heavy traffic with resource pooling: Asymptotic optimality of a threshold policy
• Asymptotic optimality of tracking policies in stochastic networks.
• Discrete-review policies for scheduling stochastic networks: trajectory tracking and fluid-scale asymptotic optimality.
• A unified perturbation analysis framework for countable Markov chains
• Fluctuation smoothing policies are stable for stochastic re-entrant lines
• A fluid limit model criterion for instability of multiclass queueing networks
• Robust Fluid Processing Networks
• Uniformization for semi-Markov decision processes under stationary policies
• Technical Note—An Equivalence Between Continuous and Discrete Time Markov Decision Processes
• Performance Analysis of Queueing Networks via Robust Optimization
• Markov Chains and Stochastic Stability
• The Linear Programming Approach to Approximate Dynamic Programming
• Stable, distributed, real-time scheduling of flexible manufacturing/assembly/diassembly systems
• Heavy Traffic Convergence of a Controlled, Multiclass Queueing System
• Dynamic Scheduling of a Multiclass Fluid Network
• Performance bounds for queueing networks and scheduling policies
• OnActor-Critic Algorithms
• CONVERGENCE OF SIMULATION-BASED POLICY ITERATION
• Simulation-based optimization of Markov reward processes
• Applied Probability and Queues
• Variance reduction through smoothing and control variates for Markov chain simulations
• Processing Networks
• Scheduling Networks of Queues: Heavy Traffic Analysis of a Two-Station Closed Network
• Target-Pursuing Scheduling and Routing Policies for Multiclass Queueing Networks
• Approximating Martingales for Variance Reduction in Markov Process Simulation

This page was built for publication: Queueing Network Controls via Deep Reinforcement Learning