Cooperative Multi-Agent Assignment over Stochastic Graphs via Constrained Reinforcement Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909516247859200 |
|---|---|
| author | Agorio, Leopoldo Van Alen, Sean Paternain, Santiago Calvo-Fullana, Miguel Bazerque, Juan Andres |
| author_facet | Agorio, Leopoldo Van Alen, Sean Paternain, Santiago Calvo-Fullana, Miguel Bazerque, Juan Andres |
| contents | Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to carry out conflicting tasks. We address the challenges of multi-agent coordination through an unconventional formulation in which the dual variables are not driven to convergence but are free to cycle, enabling agents to adapt their policies dynamically based on real-time constraint satisfaction levels. The coordination relies on a light single-bit communication protocol over a network with stochastic connectivity. Using this gossiped information, agents update local estimates of the dual variables. Furthermore, we modify the local dual dynamics by introducing a contraction factor, which lets us use finite communication buffers and keep the estimation error bounded. Under this model, we provide theoretical guarantees of almost sure feasibility and corroborate them with numerical experiments in which a team of robots successfully patrols multiple regions, communicating under a time-varying ad-hoc network. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20462 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cooperative Multi-Agent Assignment over Stochastic Graphs via Constrained Reinforcement Learning Agorio, Leopoldo Van Alen, Sean Paternain, Santiago Calvo-Fullana, Miguel Bazerque, Juan Andres Systems and Control Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to carry out conflicting tasks. We address the challenges of multi-agent coordination through an unconventional formulation in which the dual variables are not driven to convergence but are free to cycle, enabling agents to adapt their policies dynamically based on real-time constraint satisfaction levels. The coordination relies on a light single-bit communication protocol over a network with stochastic connectivity. Using this gossiped information, agents update local estimates of the dual variables. Furthermore, we modify the local dual dynamics by introducing a contraction factor, which lets us use finite communication buffers and keep the estimation error bounded. Under this model, we provide theoretical guarantees of almost sure feasibility and corroborate them with numerical experiments in which a team of robots successfully patrols multiple regions, communicating under a time-varying ad-hoc network. |
| title | Cooperative Multi-Agent Assignment over Stochastic Graphs via Constrained Reinforcement Learning |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2502.20462 |