---
title: "Zeroth-Order Policy Optimization for Scheduling in Queueing Networks"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.01186v1"
permalink: "https://feed.astralor.com/items/itm_9f934a5eeca3aff7d58c0730"
published: "2026-10-31T18:37:20.000Z"
score: 53
channel: "tech"
tags: ["RAG","Zeroth-Order Policy Optimization","Scheduling","Queueing Networks Reinforcement","Reinforcement","Our","Building","Numerical"]
---

# Zeroth-Order Policy Optimization for Scheduling in Queueing Networks

## At a glance

Reinforcement learning in queueing network scheduling presents significant challenges because of the countably infinite state space and the high stochasticity in transitions. In this paper, we propose zeroth-order polic…

## Key points

- Reinforcement learning in queueing network scheduling presents significant challenges because of the countably infinite state space and the high stochasticity in transitions.
- In this paper, we propose zeroth-order policy optimization algorithms that are easy to implement and rely solely on estimates of the average cost, a single scalar quantity, without requiring the estimation of value or a…
- Our analysis focuses on back-pressure guarded policies and establishes uniform smoothness of the average cost objective with respect to the policy parameters.

## Full text

Reinforcement learning in queueing network scheduling presents significant challenges because of the countably infinite state space and the high stochasticity in transitions. In this paper, we propose zeroth-order policy optimization algorithms that are easy to implement and rely solely on estimates of the average cost, a single scalar quantity, without requiring the estimation of value or advantage functions. Our analysis focuses on back-pressure guarded policies and establishes uniform smoothness of the average cost objective with respect to the policy parameters. Building on this property, we establish finite-time convergence guarantees to an $ε$-stationary policy for the proposed algorithms. Numerical experiments on multiple queueing networks, including systems beyond classical exponential service distribution, demonstrate competitive performance, outperforming gradient-based RL methods like PPO and traditional queueing baselines.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_9f934a5eeca3aff7d58c0730