mlsanityData to 14 Oct 2026

Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning

arXiv 2509.16606 ↗First posted 20 Sep 2025cs.MA cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

In networked multi-agent reinforcement learning (Networked-MARL), decentralized agents must act under local observability and constrained communication over fixed physical graphs. Existing methods often assume static neighborhoods, limiting adaptability to dynamic or heterogeneous environments. While centralized frameworks can learn dynamic graphs, their reliance on global state access and centralized infrastructure is impractical in real-world decentralized systems. We propose a stochastic graph-based policy for Networked-MARL, where each agent conditions its decision on a sampled subgraph over its local physical neighborhood. Building on this formulation, we introduce BayesG, a decentralized actor-framework that learns sparse, context-aware interaction structures via Bayesian variational inference. Each agent operates over an ego-graph and samples a latent communication mask to guide message passing and policy computation. The variational distribution is trained end-to-end alongside the policy using an evidence lower bound (ELBO) objective, enabling agents to jointly learn both interaction topology and decision-making strategies. BayesG outperforms strong MARL baselines on large-scale traffic control tasks with up to 167 agents, demonstrating superior scalability, efficiency, and performance.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 38 of its 56 references that are in the map. First posted on arXiv 20 Sep 2025.

Builds on

38 of 56 references.

References · 38

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  6. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  7. 2019The StarCraft Multi-Agent Challengecited by 597
  8. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  9. 2016Learning Multiagent Communication with Backpropagationcited by 366
  10. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
  11. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 194
  12. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
26 more
  1. 2018Graph Convolutional Reinforcement Learningcited by 152
  2. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 137
  3. 2017Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learningcited by 117
  4. 2019Deep Coordination Graphscited by 98
  5. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 82
  6. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  7. 2020Multi-agent Reinforcement Learning for Networked System Controlcited by 53
  8. 2020Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Rewardcited by 50
  9. 2020Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learningcited by 42
  10. 2020Multi-Agent Reinforcement Learning in Stochastic Networked Systemscited by 32
  11. 2021Context-Aware Sparse Deep Coordination Graphscited by 28
  12. 2024Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwardscited by 19
  13. 2024Group-Aware Coordination Graph for Multi-Agent Reinforcement Learningcited by 18
  14. 2023Online Boosting Adaptive Learning under Concept Drift for Multistream Classificationcited by 17
  15. 2024One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representationcited by 16
  16. 2021Self-Organized Polynomial-Time Coordination Graphscited by 15
  17. 2025Learning Robust Spectral Dynamics for Temporal Domain Generalizationcited by 14
  18. 2025Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learningcited by 14
  19. 2024Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scalecited by 8
  20. 2022Scalable Model-based Policy Optimization for Decentralized Networked Systemscited by 7
  21. 2022Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processescited by 7
  22. 2024Layer-diverse Negative Sampling for Graph Neural Networkscited by 7
  23. 2024Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learningcited by 7
  24. 2025Resilient Contrastive Pre-training under Non-Stationary Driftcited by 7
  25. 2025Generalized Incremental Learning under Concept Drift across Evolving Data Streamscited by 7
  26. 2025Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learningcited by 0
  2. 2026BARD-MARL: Byzantine-Agent Detection for Learned Communication in Multi-Agent Reinforcement Learningcited by 0
  3. 2026Synergizing Drone Delivery Order Pooling and Road Network Monitoring through Monitoring-Task Orderizationcited by 0
  4. 2026Continual Graph Multi-Agent Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
  2. 2025Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective
  3. 2024Scaling Team Coordination on Graphs with Reinforcement Learning
  4. 2026Coordination Graphs for Constrained Multi-Agent Reinforcement Learning
  5. 2024Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing
  6. 2026Do LLM-derived graph priors improve multi-agent coordination?
  7. 2025Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning
  8. 2026Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning