Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
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_ | 1866909864500920320 |
|---|---|
| author | Fox, Andrea De Pellegrini, Francesco Altman, Eitan |
| author_facet | Fox, Andrea De Pellegrini, Francesco Altman, Eitan |
| contents | In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability and communication constraints. We propose a decentralized framework in which each agent solves a constrained Markov decision process (CMDP), coordinating implicitly through a shared constraint vector. For the specific case of offloading, e.g., constraints prevent overloading shared server resources. Coordination constraints are updated infrequently and act as a lightweight coordination mechanism. They enable agents to align with global resource usage objectives but require little direct communication. Using safe reinforcement learning, agents learn policies that meet both local and global goals. We establish theoretical guarantees under mild assumptions and validate our approach experimentally, showing improved performance over centralized and independent baselines, especially in large-scale settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01257 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks Fox, Andrea De Pellegrini, Francesco Altman, Eitan Machine Learning Artificial Intelligence Networking and Internet Architecture In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability and communication constraints. We propose a decentralized framework in which each agent solves a constrained Markov decision process (CMDP), coordinating implicitly through a shared constraint vector. For the specific case of offloading, e.g., constraints prevent overloading shared server resources. Coordination constraints are updated infrequently and act as a lightweight coordination mechanism. They enable agents to align with global resource usage objectives but require little direct communication. Using safe reinforcement learning, agents learn policies that meet both local and global goals. We establish theoretical guarantees under mild assumptions and validate our approach experimentally, showing improved performance over centralized and independent baselines, especially in large-scale settings. |
| title | Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks |
| topic | Machine Learning Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2509.01257 |