mlsanityData to 14 Oct 2026

From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control

arXiv 2609.03590 ↗First posted 3 Sep 2026cs.NI cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Offline multi-agent RL

Abstract (arXiv)

Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is essential for NextG interactive applications, yet providing strict End-to-End (E2E) peak latency guarantees remains an open challenge. Two obstacles limit the adoption of learning-based network control in this setting: traditional volume-based routing metrics, while highly effective for general traffic management, are not designed to capture traffic urgency; and Deep Reinforcement Learning (DRL) controllers trained from scratch suffer from sample inefficiency, long training times, and early-stage exploration volatility. This paper introduces a deployment-focused network control framework that addresses both obstacles. First, we present Effective Congestion (EC), a deadline-aware metric family that quantifies interface congestion by packet urgency and proactively filters non-viable traffic, coupled with a Uniform Path Grouping (UPG) distribution heuristic promoting robust load-balancing; the resulting policies are embedded into Multi-Agent Deep Reinforcement Learning Effective Congestion (p^*) (MADRL EC (p^*)), a hybrid architecture combining a distributed scheduler with a centralized RL-based router. Second, we introduce a unified training objective that generalizes existing policy-learning paradigms---behavioral cloning, offline Reinforcement Learning (RL), online RL, and offline-to-online schemes---as special cases, combining a live-reward term, a pre-collected-reward term, and a policy-imitation term. From this objective, we derive the Model-Guided Annealed Reinforcement Learning (MGA-RL) protocol, instantiated on a Deep Deterministic Policy Gradient (DDPG) backbone: a deployment-oriented, demonstration-driven training approach that generalizes conventional Offline-to-Online (O2O) schemes, in which trajectories from a lightweight [...]

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Offline multi-agent RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 16 of its 35 references that are in the map. First posted on arXiv 3 Sep 2026.

Builds on

16 of 35 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  5. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  6. 2023Mastering Diverse Domains through World Modelscited by 1,253
  7. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
  8. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  9. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 340
  10. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 319
  11. 2018Reinforcement Learning from Imperfect Demonstrationscited by 75
  12. 2019Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidancecited by 25
4 more
  1. 2022Compute- and Data-Intensive Networks: The Key to the Metaversecited by 9
  2. 2016Optimal Control for Generalized Network-Flow Problemscited by 4
  3. 2022Ultra-Reliable Distributed Cloud Network Control with End-to-End Latency Constraintscited by 3
  4. 2017Optimal Dynamic Cloud Network Controlcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services
  2. 2026A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications
  3. 2026Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks
  4. 2024Towards Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges
  5. 2026Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints
  6. 2026Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks
  7. 2024A Deep Reinforcement Learning Approach for Adaptive Traffic Routing in Next-gen Networks
  8. 2024Towards Fair and Efficient Learning-based Congestion Control