Metraipolis › archive › dc_c2d12089e55e

Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning — arXiv:2609.03667

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03667
License (as archived)
CC0-1.0
Archived
2026-10-17T01:12:03.259Z
SHA-256 of the archived text
545f9c51f9c48e6dcd05788f96b58577531945bb4ac1cacb7fa660c557c8a1b8
Stable URL of this page
https://metraipolis.com/documento/dc_c2d12089e55e

How to cite

Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning — arXiv:2609.03667 — arXiv (en), https://arxiv.org/abs/2609.03667 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2d12089e55e (Metraipolis archive dc_c2d12089e55e, sha256 545f9c51f9c48e6dcd05788f96b58577531945bb4ac1cacb7fa660c557c8a1b8)
BibTeX
@misc{dcc2d12089e55e,
  title = {Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning — arXiv:2609.03667},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03667},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2d12089e55e; sha256 545f9c51f9c48e6dcd05788f96b58577531945bb4ac1cacb7fa660c557c8a1b8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03667. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generalising to unseen tasks remains a fundamental challenge in offline multi-agent reinforcement learning (MARL). In this work, we present a principled analysis of zero-shot task generalisation in the offline setting and conduct an extensive empirical investigation into the scaling behaviour governing task diversity, dataset size, and network capacity. To facilitate this study, we extend offline sequence modelling architectures to handle multi-task observation and action spaces alongside variable agent counts across tasks. Our primary finding is that scaling task diversity---rather than sheer dataset size is the dominant factor in achieving robust zero-shot transfer. Through large-scale experiments across four challenging environments (Connector, RWARE, SMAX, and LBF), we demonstrate that our multi-task approach achieves a mean improvement of 3.2x on held-out test tasks compared to single-task models and consistently outperforms strong behaviour cloning baselines. These results suggest that the development of generalisable MARL agents should prioritise the diversity of the training distribution with varying numbers of agents, providing a roadmap for scaling offline MARL effectively.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03667 — 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 2026-10-17T00:28:02.994Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).