mlsanityData to 14 Oct 2026

Signal attenuation enables scalable decentralized multi-agent reinforcement learning over networks

arXiv 2505.11461 ↗First posted 16 May 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-agent reinforcement learning (MARL) methods typically require that agents enjoy global state observability, preventing development of decentralized algorithms and limiting scalability. Recent work has shown that, under assumptions on decaying inter-agent influence, global observability can be replaced by local neighborhood observability at each agent, enabling decentralization and scalability. Real-world applications enjoying such decay properties remain underexplored, however, despite the fact that signal power decay, or signal attenuation, due to path loss is an intrinsic feature of many problems in wireless communications and radar networks. In this paper, we show that signal attenuation enables decentralization in MARL by considering the illustrative special case of performing power allocation for target detection in a radar network. To achieve this, we propose two new constrained multi-agent Markov decision process formulations of this power allocation problem, derive local neighborhood approximations for global value function and policy gradient estimates and establish corresponding error bounds, and develop decentralized saddle point policy gradient algorithms for solving the proposed problems. Our approach, though oriented towards the specific radar network problem we consider, provides a useful model for extensions to additional problems in wireless communications and radar networks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

14 of 24 references.

References · 14

  1. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  2. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 194
  3. 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 177
  4. 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 151
  5. 2020A Finite Time Analysis of Two Time-Scale Actor Critic Methodscited by 122
  6. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  7. 2020Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Rewardcited by 50
  8. 2022Finite-time analysis of single-timescale actor-criticcited by 32
  9. 2019Scalable Reinforcement Learning for Multi-Agent Networked Systemscited by 24
  10. 2019A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learningcited by 21
  11. 2023Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Criticcited by 18
  12. 2016Proximity Without Consensus in Online Multi-Agent Optimizationcited by 14
2 more
  1. 2020Reinforcement Learning based Distributed Control of Dissipative Networked Systemscited by 3
  2. 2022Identifying Coordination in a Cognitive Radar Network -- A Multi-Objective Inverse Reinforcement Learning Approachcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning for Enhancing Sensing Estimation in Bistatic ISAC Systems with UAV Swarms
  2. 2024Transferable Graphical MARL for Real-Time Estimation in Dynamic Wireless Networks
  3. 2025Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
  4. 2025Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets
  5. 2026Distributed TD Tracking with Linear Function Approximation over Directed Communication Networks
  6. 2026Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks
  7. 2026Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
  8. 2026Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking