# A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services

arXiv: https://arxiv.org/abs/2510.11535 · HTML: https://mlsanity.com/paper/2510.11535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Applications of Deep Reinforcement Learning in Communications and Networking: A Survey](https://mlsanity.com/paper/1810.07862/) (2018)
- [RL-QN: A Reinforcement Learning Framework for Optimal Control of Queueing Systems](https://mlsanity.com/paper/2011.07401/) (2020)
- [Compute- and Data-Intensive Networks: The Key to the Metaverse](https://mlsanity.com/paper/2204.02001/) (2022)
- [Throughput Optimal Decentralized Scheduling of Multi-Hop Networks with End-to-End Deadline Constraints: Unreliable Links](https://mlsanity.com/paper/1606.01608/) (2016)
- [Constraint-Aware Deep Reinforcement Learning for End-to-End Resource Orchestration in Mobile Networks](https://mlsanity.com/paper/2110.04320/) (2021)
- [Optimal Control for Generalized Network-Flow Problems](https://mlsanity.com/paper/1611.08641/) (2016)
- [Ultra-Reliable Distributed Cloud Network Control with End-to-End Latency Constraints](https://mlsanity.com/paper/2205.02427/) (2022)
- [Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning](https://mlsanity.com/paper/2208.14074/) (2022)
- [Optimal Control of Distributed Computing Networks with Mixed-Cast Traffic Flows](https://mlsanity.com/paper/1805.10527/) (2018)
- [End-to-End Orchestration of NextG Media Services over the Distributed Compute Continuum](https://mlsanity.com/paper/2407.08710/) (2024)

## Abstract (arXiv)

Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is increasingly essential for a range of interactive applications, such as industrial automation, self-driving vehicles, and augmented reality. However, most existing network control solutions target only average delay performance, falling short of providing strict End-to-End (E2E) peak latency guarantees. This paper addresses the challenge of reliably delivering packets within application-imposed deadlines by leveraging recent advancements in Multi-Agent Deep Reinforcement Learning (MA-DRL). After introducing the Delay-Constrained Maximum-Throughput (DCMT) dynamic network control problem, and highlighting the limitations of current solutions, we present a novel MA-DRL network control framework that leverages a centralized routing and distributed scheduling architecture. The proposed framework leverages critical networking domain knowledge for the design of effective MA-DRL strategies based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) technique, where centralized routing and distributed scheduling agents dynamically assign paths and schedule packet transmissions according to packet lifetimes, thereby maximizing on-time packet delivery. The generality of the proposed framework allows integrating both data-driven blueDeep Reinforcement Learning (DRL) agents and traditional rule-based policies in order to strike the right balance between performance and learning complexity. Our results confirm the superiority of the proposed framework with respect to traditional stochastic optimization-based approaches and provide key insights into the role and interplay between data-driven DRL agents and new rule-based policies for both efficient and high-performance control of latency-critical services.