Metraipolis › archive › dc_d65eeb0a56ca
A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing — arXiv:2609.26783
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26783
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T15:11:40.589Z
- SHA-256 of the archived text
7d4f1dc780e794a833eb48108cb4972609548d79c83688aeb4b1e048533e8bce- Stable URL of this page
https://metraipolis.com/documento/dc_d65eeb0a56ca
How to cite
A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing — arXiv:2609.26783 — arXiv (en), https://arxiv.org/abs/2609.26783 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d65eeb0a56ca (Metraipolis archive dc_d65eeb0a56ca, sha256 7d4f1dc780e794a833eb48108cb4972609548d79c83688aeb4b1e048533e8bce)
BibTeX
@misc{dcd65eeb0a56ca,
title = {A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing — arXiv:2609.26783},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26783},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d65eeb0a56ca; sha256 7d4f1dc780e794a833eb48108cb4972609548d79c83688aeb4b1e048533e8bce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26783. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study decentralized partially observable team decision problems with low-rank latent dynamics and unknown system models. The proposed framework combines team-theoretic equivalence with low-rank model representations to address cooperative decision-making in partially observable Markov decision processes without prior knowledge of the transition model. Each team member makes decisions based on local private information and delayed common information shared across the team. Using only this available information, each member learns an approximate low-rank Markov decision process and applies least-squares value iteration to compute its policy. This yields a fully decentralized learning and planning algorithm that requires neither a centralized coordinator nor centralized training. We show that the resulting member-side solutions approximate the centralized team solution: despite partial observability, unknown dynamics, and delayed common information, each member recovers the corresponding component of an approximate team-optimal policy. We further establish finite-sample performance guarantees and derive a corresponding sample-complexity bound for the proposed algorithm. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG). Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Systems and Control (eess.SY); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.26783 — 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 2026-10-08T14:37:29.593Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).