mlsanityData to 14 Oct 2026

Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems

arXiv 2503.15172 ↗First posted 19 Mar 2025cs.LG cs.AI cs.NIcited by 1

Not on the map. Why?

Abstract (arXiv)

Multi-Agent Deep Reinforcement Learning (MADRL) has emerged as a powerful tool for optimizing decentralized decision-making systems in complex settings, such as Dynamic Spectrum Access (DSA). However, deploying deep learning models on resource-constrained edge devices remains challenging due to their high computational cost. To address this challenge, in this paper, we present a novel sparse recurrent MARL framework integrating gradual neural network pruning into the independent actor global critic paradigm. Additionally, we introduce a harmonic annealing sparsity scheduler, which achieves comparable, and in certain cases superior, performance to standard linear and polynomial pruning schedulers at large sparsities. Our experimental investigation demonstrates that the proposed DSA framework can discover superior policies, under diverse training conditions, outperforming conventional DSA, MADRL baselines, and state-of-the-art pruning techniques.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 27 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

15 of 27 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
  6. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  7. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
  8. 2020Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learningcited by 134
  9. 2022The State of Sparse Training in Deep Reinforcement Learningcited by 61
  10. 2024In value-based deep reinforcement learning, a pruned network is a good networkcited by 39
  11. 2018Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networkscited by 37
  12. 2020PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learningcited by 30
3 more
  1. 2023Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learningcited by 14
  2. 2021Dynamic Channel Access and Power Control in Wireless Interference Networks via Multi-Agent Deep Reinforcement Learningcited by 5
  3. 2016Optimizing Access Mechanisms for QoS Provisioning in Hardware Constrained Dynamic Spectrum Accesscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Active Sensing for RIS-Aided Tracking and Power Control: A Hybrid Neuroevolution and Supervised Learning Approachcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
  2. 2025Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning
  3. 2025Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks
  4. 2026Scalable Neighborhood-Based Multi-Agent Actor-Critic
  5. 2026SliceFed: Federated Constrained Multi-Agent DRL for Dynamic Spectrum Slicing in 6G ↗
  6. 2024Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
  7. 2025SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks
  8. 2024SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks