Metraipolis › archive › dc_0ecd4d1e40d4

SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning — arXiv:2610.30443

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30443
License (as archived)
CC0-1.0
Archived
2026-10-23T15:12:50.458Z
SHA-256 of the archived text
cd31349817cdb82581509c2592d565c08dc16cbf4cecf97f502c6d32dfc5febb
Stable URL of this page
https://metraipolis.com/documento/dc_0ecd4d1e40d4

How to cite

SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning — arXiv:2610.30443 — arXiv (en), https://arxiv.org/abs/2610.30443 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ecd4d1e40d4 (Metraipolis archive dc_0ecd4d1e40d4, sha256 cd31349817cdb82581509c2592d565c08dc16cbf4cecf97f502c6d32dfc5febb)
BibTeX
@misc{dc0ecd4d1e40d4,
  title = {SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning — arXiv:2610.30443},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30443},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ecd4d1e40d4; sha256 cd31349817cdb82581509c2592d565c08dc16cbf4cecf97f502c6d32dfc5febb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30443. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across complex, temporally extended tasks with diverse inter-agent coordination requirements. We introduce a specification language that combines temporal-logic task specifications with operators for expressing such requirements. We propose SpecMAGIC, a hierarchical framework that leverages the automaton structure of task specifications for subtask decomposition. A centralized high-level planner identifies and allocates compatible subtask sequences across agents, while decentralized low-level policies execute individual subtasks. This enables zero-shot generalization to new tasks by composing reusable subtask policies according to new specifications, without retraining. We establish soundness and probabilistic completeness of the high-level planner. Experiments on multi-agent navigation tasks show that SpecMAGIC substantially outperforms existing approaches on unseen task specifications and maintains strong performance as the number of agents increases.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30443 — 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 2026-10-23T15:09:08.361Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).