Metraipolis › archive › dc_5e9e748e91d2
An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems — arXiv:2611.03301
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03301
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:29:46.688Z
- SHA-256 of the archived text
2c1456a7a978b977e906f07d9fc6ec22589e675ac587aca84287d9688d378fcc- Stable URL of this page
https://metraipolis.com/documento/dc_5e9e748e91d2
How to cite
An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems — arXiv:2611.03301 — arXiv (en), https://arxiv.org/abs/2611.03301 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e9e748e91d2 (Metraipolis archive dc_5e9e748e91d2, sha256 2c1456a7a978b977e906f07d9fc6ec22589e675ac587aca84287d9688d378fcc)
BibTeX
@misc{dc5e9e748e91d2,
title = {An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems — arXiv:2611.03301},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03301},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e9e748e91d2; sha256 2c1456a7a978b977e906f07d9fc6ec22589e675ac587aca84287d9688d378fcc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03301. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open multi-agent systems, where only a subset of agents are controllable, are central to real-world domains such as smart grids, yet lack a principled foundation for reinforcement learning algorithm design. We study this setting through n-agent ad hoc teamwork (NAHT), a recent framework for learning in open multi-agent environments. We propose an axiomatic framework that derives value function learning from the Shapley axioms (Efficiency, Symmetry and Linearity), treating them as structural constraints rather than heuristic design choices. This formulation builds on a novel NAHT decomposition, which characterises the fundamental difference between open and fully controllable multi-agent systems, and establishes a cooperative game-theoretic foundation for learning. We further show that enforcing these axioms on learning individual value functions recovers the Shapley value for Dec-POMDPs, providing a principled bridge between reinforcement learning and classical cooperative game theory. Building on this framework, we introduce Shapley Machines and Banzhaf Machines, two generic algorithmic templates that can be instantiated with standard reinforcement learning methods. When applied to strong base algorithms such as IPPO and POAM, our methods consistently improve learning efficiency and generalisation to unseen agent types and conventions across NAHT benchmark tasks. The code of experiments is published on this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.03301 — 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 2026-11-03T10:29:33.410Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).