Transferable Graphical MARL for Real-Time Estimation in Dynamic Wireless Networks
Not on the map. Why?
Abstract (arXiv)
We study real-time sampling and estimation of autoregressive Markovian sources in decentralized and dynamic multi-hop networks that share similar structures. Nodes cache neighboring samples and communicate over wireless collision channels. The objective is to minimize the time-average estimation error and/or the age of information under decentralized policies, which we address by developing a unified graphical multi-agent reinforcement learning framework. A key feature of the framework is its transferability, enabled by the fact that the number of trainable parameters is independent of the number of agents, allowing a learned policy to be directly deployed on dynamic yet structurally similar graphs without re-training. Building on this design, we establish rigorous theoretical guarantees on the transferability of the resulting policies. Numerical experiments demonstrate that (i) our method outperforms state-of-the-art baselines on dynamic graphs; (ii) the trained policies transfer well to larger networks, with performance gains increasing with the number of nodes; and (iii) incorporating recurrence is crucial, enhancing resilience to non-stationarity in both independent learning and centralized training with decentralized execution.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 58 references that are in the map. First posted on arXiv 4 Apr 2024.
Builds on
26 of 58 references.
References · 26
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
- 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
- 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 207
- 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 173
- 2019Stability Properties of Graph Neural Networkscited by 125
- 2020Convergence and Stability of Graph Convolutional Networks on Large Random Graphscited by 75
- 2018Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networkscited by 70
- 2020Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorialcited by 59
- 2020Gated Graph Recurrent Neural Networkscited by 57
- 2021Transferability of Graph Neural Networks: an Extended Graphon Approachcited by 51
14 more
- 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
- 2021Transferability Properties of Graph Neural Networkscited by 42
- 2020Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learningcited by 41
- 2020Graphon Signal Processingcited by 37
- 2017Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processescited by 21
- 2020Graphon Filters: Graph Signal Processing in the Limitcited by 16
- 2019Minimizing the Age of Information in Wireless Networks with Stochastic Arrivalscited by 6
- 2023Monitoring Correlated Sources: AoI-based Scheduling is Nearly Optimalcited by 4
- 2019Age of Information in Random Access Channelscited by 3
- 2020Real-time Sampling and Estimation on Random Access Channels: Age of Information and Beyondcited by 3
- 2021Learning Connectivity for Data Distribution in Robot Teamscited by 3
- 2021Information Freshness in Multi-Hop Wireless Networkscited by 3
- 2018Age of Information in Multihop Multicast Networkscited by 2
- 2022Minimizing Age of Information in Spatially Distributed Random Access Wireless Networkscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.