Metraipolis › archive › dc_33ba17fa2c0f
Social Laws for Multi-agent Coordination in Stochastic Environments — arXiv:2609.18929
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18929
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:08:12.011Z
- SHA-256 of the archived text
f9a376d5eceba2c181f9eaf2848e2518627eaaa37c4c4d44c1f725ec8725b88a- Stable URL of this page
https://metraipolis.com/documento/dc_33ba17fa2c0f
How to cite
Social Laws for Multi-agent Coordination in Stochastic Environments — arXiv:2609.18929 — arXiv (en), https://arxiv.org/abs/2609.18929 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33ba17fa2c0f (Metraipolis archive dc_33ba17fa2c0f, sha256 f9a376d5eceba2c181f9eaf2848e2518627eaaa37c4c4d44c1f725ec8725b88a)
BibTeX
@misc{dc33ba17fa2c0f,
title = {Social Laws for Multi-agent Coordination in Stochastic Environments — arXiv:2609.18929},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18929},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33ba17fa2c0f; sha256 f9a376d5eceba2c181f9eaf2848e2518627eaaa37c4c4d44c1f725ec8725b88a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18929. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous research on social laws for multi-agent systems has primarily focused on deterministic, goal-based settings. This paper extends the concept of social laws to stochastic, reward-based environments, proposing a formalism for defining and verifying their robustness under various conditions. We introduce the notion of $\alpha$-robustness, a measure of the guaranteed utility each agent retains while pursuing its optimal single agent policy, assuming all agents obey the social law. We then present an approach for robustness verification of social laws in stochastic settings, based on a reduction to solving a series of Markov decision processes. Empirical evaluations on toy environments illustrate the potential of our framework. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.18929 — 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 2026-10-15T14:08:19.288Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).