Multi-agent assignment via state augmented reinforcement learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929734956351488 |
|---|---|
| author | Agorio, Leopoldo Van Alen, Sean Calvo-Fullana, Miguel Paternain, Santiago Bazerque, Juan Andres |
| author_facet | Agorio, Leopoldo Van Alen, Sean Calvo-Fullana, Miguel Paternain, Santiago Bazerque, Juan Andres |
| contents | We address the conflicting requirements of a multi-agent assignment problem through constrained reinforcement learning, emphasizing the inadequacy of standard regularization techniques for this purpose. Instead, we recur to a state augmentation approach in which the oscillation of dual variables is exploited by agents to alternate between tasks. In addition, we coordinate the actions of the multiple agents acting on their local states through these multipliers, which are gossiped through a communication network, eliminating the need to access other agent states. By these means, we propose a distributed multi-agent assignment protocol with theoretical feasibility guarantees that we corroborate in a monitoring numerical experiment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01782 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-agent assignment via state augmented reinforcement learning Agorio, Leopoldo Van Alen, Sean Calvo-Fullana, Miguel Paternain, Santiago Bazerque, Juan Andres Systems and Control Artificial Intelligence Machine Learning Multiagent Systems 93E35 We address the conflicting requirements of a multi-agent assignment problem through constrained reinforcement learning, emphasizing the inadequacy of standard regularization techniques for this purpose. Instead, we recur to a state augmentation approach in which the oscillation of dual variables is exploited by agents to alternate between tasks. In addition, we coordinate the actions of the multiple agents acting on their local states through these multipliers, which are gossiped through a communication network, eliminating the need to access other agent states. By these means, we propose a distributed multi-agent assignment protocol with theoretical feasibility guarantees that we corroborate in a monitoring numerical experiment. |
| title | Multi-agent assignment via state augmented reinforcement learning |
| topic | Systems and Control Artificial Intelligence Machine Learning Multiagent Systems 93E35 |
| url | https://arxiv.org/abs/2406.01782 |