Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911659953487872 |
|---|---|
| author | Persson, Mika Lidman, Jonas Ljungberg, Jacob Sandelius, Samuel Andersson, Adam |
| author_facet | Persson, Mika Lidman, Jonas Ljungberg, Jacob Sandelius, Samuel Andersson, Adam |
| contents | This work studies the application of Multi-Agent Reinforcement Learning (MARL) to decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is introduced, designed for MARL scaling studies. A robust baseline policy is proposed which restricts agent motion and applies Dijkstra's shortest path algorithm. Computational experiment results show that two off-the-shelf MARL algorithms perform competitively with the baseline for a small number of agents, but face scalability issues as the number of agents increases. Source code and animations are available online at https://github.com/mikapersson/Information-Relaying. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies Persson, Mika Lidman, Jonas Ljungberg, Jacob Sandelius, Samuel Andersson, Adam Systems and Control Artificial Intelligence Computer Science and Game Theory Multiagent Systems This work studies the application of Multi-Agent Reinforcement Learning (MARL) to decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is introduced, designed for MARL scaling studies. A robust baseline policy is proposed which restricts agent motion and applies Dijkstra's shortest path algorithm. Computational experiment results show that two off-the-shelf MARL algorithms perform competitively with the baseline for a small number of agents, but face scalability issues as the number of agents increases. Source code and animations are available online at https://github.com/mikapersson/Information-Relaying. |
| title | Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies |
| topic | Systems and Control Artificial Intelligence Computer Science and Game Theory Multiagent Systems |
| url | https://arxiv.org/abs/2512.09682 |