Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910883700015104 |
|---|---|
| author | Stamatelis, George Kanatas, Angelos-Nikolaos Alexandropoulos, George C. |
| author_facet | Stamatelis, George Kanatas, Angelos-Nikolaos Alexandropoulos, George C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15172 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems Stamatelis, George Kanatas, Angelos-Nikolaos Alexandropoulos, George C. Machine Learning Artificial Intelligence Networking and Internet Architecture 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. |
| title | Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems |
| topic | Machine Learning Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2503.15172 |