mlsanityData to 14 Oct 2026

FedCritic-MIMO: Communication-Efficient Serverless Federated Critic Learning for Massive-MIMO Resource Control in Open and Disaggregated 6G RANs

arXiv 2608.03852 ↗First posted 4 Aug 2026cs.LG cs.MA cs.NIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes FedCritic-MIMO, a communication-efficient serverless federated multi-agent reinforcement learning framework for AI-native resource control across independently deployable cell-level controllers in open and disaggregated 6G RANs. Controllers share no trainer, retain local actors and personalized critic components, and exchange only compatible shared critic parameters. FedCritic-MIMO targets reuse-1 multi-cell massive-MIMO OFDMA deployments, where RAN controllers jointly manage user scheduling, per-stream power allocation, beamforming, interference, and long-term QoS with limited inter-controller signaling. Each base station locally executes its actor without centralized training or actor federation, while critic knowledge is exchanged peer-to-peer over an interference-aware graph. It enables this collaboration through wireless-aware event triggering, adaptive layer-wise top-k sparse critic exchange with error feedback, and balanced interference-aware fusion. We establish conditional finite-time stationarity and consensus guarantees for the balanced, compressed peer-to-peer critic recursion under a fixed-policy, frozen-target critic-regression model. In strongly interference-coupled reuse-1 simulations, FedCritic-MIMO achieves the best performance-communication tradeoff among heuristic, independent-learning, centralized-training, and communication-ablation baselines. It achieves the highest held-out throughput, improves user-rate distribution and mean SINR, increases QoS satisfaction, and attains the lowest interference cost per delivered bit among learning baselines. It reduces critic-communication overhead by 76% relative to uncompressed distributed critic exchange. These results demonstrate that serverless exchange of compatible shared critic parameters can coordinate RAN controllers without centralized trajectory collection or parameter-server aggregation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 4 Aug 2026.

Builds on

20 of 37 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 310
  4. 2019Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communicationcited by 221
  5. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 194
  6. 2018Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networkscited by 70
  7. 2024An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learningcited by 50
  8. 2020Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learningcited by 42
  9. 2021Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Surveycited by 34
  10. 2021Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysiscited by 26
  11. 2022Federated Deep Reinforcement Learning for Resource Allocation in O-RAN Slicingcited by 14
  12. 2023Empowering the 6G Cellular Architecture with Open RANcited by 10
8 more
  1. 2023Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networkscited by 9
  2. 2025Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6Gcited by 7
  3. 2024Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Surveycited by 5
  4. 2023Meta Federated Reinforcement Learning for Distributed Resource Allocationcited by 4
  5. 20256G Cellular Networks: Mapping the Landscape for the IMT-2030 Frameworkcited by 3
  6. 2023Communication-Efficient Soft Actor-Critic Policy Collaboration via Regulated Segment Mixturecited by 2
  7. 2025Pareto Actor-Critic for Communication and Computation Co-Optimization in Non-Cooperative Federated Learning Servicescited by 1
  8. 2026FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6Gcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning
  2. 2024Accelerating Energy-Efficient Federated Learning in Cell-Free Networks with Adaptive Quantization
  3. 2026Energy Saving for Cell-Free Massive MIMO Networks: A Multi-Agent Deep Reinforcement Learning Approach
  4. 2024Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networks
  5. 2024Multi-agent Reinforcement Learning for Energy Saving in Multi-Cell Massive MIMO Systems
  6. 2025Small-Scale-Fading-Aware Resource Allocation in Wireless Federated Learning
  7. 2026EARL: Energy-Aware Adaptive Antenna Control with Reinforcement Learning in O-RAN Cell-Free Massive MIMO Networks ↗
  8. 2025Federated Multi-Agent Reinforcement Learning for Privacy-Preserving and Energy-Aware Resource Management in 6G Edge Networks