Metraipolis › archive › dc_ba91a57570bb
Submodular Policy Learning for Distributed Task Allocation in Open Multi-Agent Systems — arXiv:2608.14390
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14390
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:19:28.259Z
- SHA-256 of the archived text
07c3ce58226227ebb84d78872c0ea4eb6f55ceccbd3bc34c9a611545452687db- Stable URL of this page
https://metraipolis.com/documento/dc_ba91a57570bb
How to cite
Submodular Policy Learning for Distributed Task Allocation in Open Multi-Agent Systems — arXiv:2608.14390 — arXiv (en), https://arxiv.org/abs/2608.14390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba91a57570bb (Metraipolis archive dc_ba91a57570bb, sha256 07c3ce58226227ebb84d78872c0ea4eb6f55ceccbd3bc34c9a611545452687db)
BibTeX
@misc{dcba91a57570bb,
title = {Submodular Policy Learning for Distributed Task Allocation in Open Multi-Agent Systems — arXiv:2608.14390},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14390},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba91a57570bb; sha256 07c3ce58226227ebb84d78872c0ea4eb6f55ceccbd3bc34c9a611545452687db},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper studies policy learning for distributed task allocation in open multi-agent systems, where agents may join and leave in a time-varying fashion, with submodular stage team utilities. At each time, the active agents select actions from local categorical policies such that the feasible joint agent-action pairs form a partition matroid. Standard continuous relaxations of submodular set functions are based on independent Bernoulli sampling, making them inconsistent with agents' this http URL solve this mismatch, we propose the \emph{partition multilinear extension} (PME), a policy-based relaxation whose continuous support matches feasible actions under categorical this http URL prove that the marginal gains of the stage utility provide an unbiased estimator of the gradient of the PME and that maximizing the PME over action distributions is equivalent to maximizing the stage utilities over agent actions, which are critical to devise principled policy this http URL on this, we design \emph{SubMAPL}, a centralized-training decentralized-execution KL-mirror policy-learning method that uses local marginal gains as stochastic PME gradients during training. KL-mirror updates preserve categorical feasibility without Euclidean this http URL the case where agents run tabular-softmax policies, we introduce open policy migration and an open-system KL tracking variation to handle agent arrivals and departures. Using dynamic regret analysis, we establish a lower bound on the cumulative utility which accounts for the openness of the environment and for the gap between optimal stage-wise and global utilities. Simulations on multi-agent coverage demonstrate that SubMAPL outperforms policy-gradient and online-learning baselines.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.14390 — 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 2026-10-19T02:01:30.008Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).