Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements
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_ | 1866910018209579008 |
|---|---|
| author | Marino, Antonio Restrepo, Esteban Pacchierotti, Claudio Giordano, Paolo Robuffo |
| author_facet | Marino, Antonio Restrepo, Esteban Pacchierotti, Claudio Giordano, Paolo Robuffo |
| contents | This paper addresses the challenge of allocating heterogeneous resources among multiple agents in a decentralized manner. Our proposed method, Liquid-Graph-Time Clustering-IPPO, builds upon Independent Proximal Policy Optimization (IPPO) by integrating dynamic cluster consensus, a mechanism that allows agents to form and adapt local sub-teams based on resource demands. This decentralized coordination strategy reduces reliance on global information and enhances scalability. We evaluate LGTC-IPPO against standard multi-agent reinforcement learning baselines and a centralized expert solution across a range of team sizes and resource distributions. Experimental results demonstrate that LGTC-IPPO achieves more stable rewards, better coordination, and robust performance even as the number of agents or resource types increases. Additionally, we illustrate how dynamic clustering enables agents to reallocate resources efficiently also for scenarios with discharging resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02437 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements Marino, Antonio Restrepo, Esteban Pacchierotti, Claudio Giordano, Paolo Robuffo Machine Learning This paper addresses the challenge of allocating heterogeneous resources among multiple agents in a decentralized manner. Our proposed method, Liquid-Graph-Time Clustering-IPPO, builds upon Independent Proximal Policy Optimization (IPPO) by integrating dynamic cluster consensus, a mechanism that allows agents to form and adapt local sub-teams based on resource demands. This decentralized coordination strategy reduces reliance on global information and enhances scalability. We evaluate LGTC-IPPO against standard multi-agent reinforcement learning baselines and a centralized expert solution across a range of team sizes and resource distributions. Experimental results demonstrate that LGTC-IPPO achieves more stable rewards, better coordination, and robust performance even as the number of agents or resource types increases. Additionally, we illustrate how dynamic clustering enables agents to reallocate resources efficiently also for scenarios with discharging resources. |
| title | Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.02437 |