Metraipolis › archive › dc_31f86d0eef60

History Matters: Meta-policy Delegation with Heterogeneous Multi-agent Reinforcement Learning — arXiv:2608.03833

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03833
License (as archived)
CC0-1.0
Archived
2026-10-31T12:14:36.370Z
SHA-256 of the archived text
40939f34583c5414719fa2d1093419184cbe2584c49eddf927e76adfa4531c60
Stable URL of this page
https://metraipolis.com/documento/dc_31f86d0eef60

How to cite

History Matters: Meta-policy Delegation with Heterogeneous Multi-agent Reinforcement Learning — arXiv:2608.03833 — arXiv (en), https://arxiv.org/abs/2608.03833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31f86d0eef60 (Metraipolis archive dc_31f86d0eef60, sha256 40939f34583c5414719fa2d1093419184cbe2584c49eddf927e76adfa4531c60)
BibTeX
@misc{dc31f86d0eef60,
  title = {History Matters: Meta-policy Delegation with Heterogeneous Multi-agent Reinforcement Learning — arXiv:2608.03833},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03833},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31f86d0eef60; sha256 40939f34583c5414719fa2d1093419184cbe2584c49eddf927e76adfa4531c60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents are expected to play an increasingly important role in future decision-making systems. In this paper, we consider collaborative systems composed of heterogeneous multi-agent systems (MAS), where their members have different capabilities and operating costs. We study how agents can delegate tasks to one another so that certain research tasks can be completed effectively under resource-constrained scenarios. We first develop a multi-agent reinforcement learning-based (MARL) delegation training that enables agents to make sequential delegation decisions while minimizing the total execution cost. We then extend this approach to MARL with prescribed delegation topologies. Furthermore, we introduce two new frameworks for collaboration and delegation in multi-agent systems. The first framework proposes that an agent's policy depends not only on the current state of the underlying Markov decision process but also on the interaction history, including previous joint actions. This history-dependent formulation can improve coordination even in fully observable environments, where conventional MARL methods typically restrict policies to depend only on the current state. The second framework proposes a novel, potentially multi-dimensional monetary mechanism to facilitate the collaboration and delegation for MAS.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.03833 — 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 2026-10-31T12:05:27.216Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).