Metraipolis › archive › dc_b11aa84cd808
Fully Decentralized and Safety-Aware Multi-Agent Reinforcement Learning for Control on Networks — arXiv:2609.36292
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36292
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:21:24.119Z
- SHA-256 of the archived text
a474a784efe5ec17a38f43214412f5e33c70e877b334320e533f37e3c6908fda- Stable URL of this page
https://metraipolis.com/documento/dc_b11aa84cd808
How to cite
Fully Decentralized and Safety-Aware Multi-Agent Reinforcement Learning for Control on Networks — arXiv:2609.36292 — arXiv (en), https://arxiv.org/abs/2609.36292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b11aa84cd808 (Metraipolis archive dc_b11aa84cd808, sha256 a474a784efe5ec17a38f43214412f5e33c70e877b334320e533f37e3c6908fda)
BibTeX
@misc{dcb11aa84cd808,
title = {Fully Decentralized and Safety-Aware Multi-Agent Reinforcement Learning for Control on Networks — arXiv:2609.36292},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36292},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b11aa84cd808; sha256 a474a784efe5ec17a38f43214412f5e33c70e877b334320e533f37e3c6908fda},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper develops a safe and fully decentralized multi-agent reinforcement learning (MARL) algorithm to solve a class of discrete-time control problems on networks, including the persistent monitoring problem. Fully decentralized control of agents, while offering numerous benefits, faces issues such as exponentially increasing sample complexity, lack of global information about the system, and challenges in coordinating between agents. To address these issues, this paper introduces a fully decentralized multi-agent reinforcement learning algorithm that integrates deep reinforcement learning with safety considerations. This method feeds a history of local observations of the network's state into two parallel neural-network branches: the graph encoder, which adds structural information and correlations among nodes, and a state estimator, which predicts the uncertainty at each node in the graph. Additionally, the result of feeding that input into an actor-critic network is passed through a discrete-time control barrier heuristic to reduce the likelihood that any node will be neglected. This approach enables teams of fully decentralized agents to solve challenging problems by increasing system awareness and incorporating built-in safety measures to prevent the adoption of potentially harmful control policies. Numerical results from a custom simulation environment demonstrate that the proposed algorithm achieves 26.3 percent lower average uncertainty than a centralized control policy and is within 1 percent of the uncertainty performance of a more computationally complex algorithm with added attention layers. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.MA). Categorie arXiv: Systems and Control (eess.SY) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.36292 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:11.823Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).