Metraipolis › archive › dc_9504488c014d

MATES: Learning Multi-Agent Interactions by Transforming Observations for Frozen Single-Agent Policies — arXiv:2609.26010

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26010
License (as archived)
CC0-1.0
Archived
2026-10-08T13:43:35.664Z
SHA-256 of the archived text
292448c55c96175f0d65dbf8fa133513f097955f8caebf191dc454496273d9cb
Stable URL of this page
https://metraipolis.com/documento/dc_9504488c014d

How to cite

MATES: Learning Multi-Agent Interactions by Transforming Observations for Frozen Single-Agent Policies — arXiv:2609.26010 — arXiv (en), https://arxiv.org/abs/2609.26010 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9504488c014d (Metraipolis archive dc_9504488c014d, sha256 292448c55c96175f0d65dbf8fa133513f097955f8caebf191dc454496273d9cb)
BibTeX
@misc{dc9504488c014d,
  title = {MATES: Learning Multi-Agent Interactions by Transforming Observations for Frozen Single-Agent Policies — arXiv:2609.26010},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26010},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9504488c014d; sha256 292448c55c96175f0d65dbf8fa133513f097955f8caebf191dc454496273d9cb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26010. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent reinforcement learning (MARL) commonly trains decentralized policies from scratch, requiring agents to acquire individual task competence and coordination simultaneously. Yet many multi-agent problems admit a compatible single-agent counterpart in which the underlying task can be learned in isolation. We introduce Multi-Agent Observation Transformation for Existing Single-Agent Policies (MATES), an input-side adaptation framework for tasks whose multi-agent observations preserve the solo-task information while exposing separately identifiable neighbor information. From multi-agent experience, MATES learns a small adapter that maps this observation into the format expected by a frozen single-agent policy, inducing actions suited to the shared environment without updating the single-agent policy itself. MATES leaves the pretrained policy's internal architecture unchanged and retains the objectives and update procedures of the underlying MARL algorithm. We evaluate MATES using both on- and off-policy algorithms on lifelong pathfinding, navigation, and cooperative discovery, spanning discrete and continuous observation and action spaces. Across all evaluated settings, MATES optimizes only 3.5-7.3% as many parameters as full-policy training while consistently outperforming MARL training from scratch. It approaches the performance of full fine-tuning, remains competitive overall with demonstration-based baselines, and retains strong task performance at team sizes not encountered during training. These results provide evidence that, under this observation structure, effective multi-agent behavior can be learned without modifying the policy that encodes individual competence.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Robotics (cs.RO); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.26010 — 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 2026-10-08T13:18:03.289Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).