Metraipolis › archive › dc_094959fdf12d

PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3 — arXiv:2608.04905

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04905
License (as archived)
CC0-1.0
Archived
2026-10-31T11:50:04.301Z
SHA-256 of the archived text
929b23fd644390189c01415aa9a64f75120b6b89fd13a37d12a4b60a2107c1d9
Stable URL of this page
https://metraipolis.com/documento/dc_094959fdf12d

How to cite

PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3 — arXiv:2608.04905 — arXiv (en), https://arxiv.org/abs/2608.04905 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_094959fdf12d (Metraipolis archive dc_094959fdf12d, sha256 929b23fd644390189c01415aa9a64f75120b6b89fd13a37d12a4b60a2107c1d9)
BibTeX
@misc{dc094959fdf12d,
  title = {PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3 — arXiv:2608.04905},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04905},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_094959fdf12d; sha256 929b23fd644390189c01415aa9a64f75120b6b89fd13a37d12a4b60a2107c1d9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04905. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present PRIMAL3, an ultra-large-scale learning-based framework for multi-agent pathfinding (MAPF) that integrates reinforcement learning, topology-aware communication, LaCAM3-guided training, and PIBT-based action refinement. PRIMAL3 targets failures at topologically critical states, where agents must coordinate decisively around bottlenecks, dead ends, and persistent conflicts. Each agent is represented using features derived from cut vertices, dead-end regions, shortest-path distances, and blocking estimates. Two complementary graphs capture agent interactions: a same-direction following graph propagates multihop context along compatible paths, while a different-direction conflict graph differentiates agents competing for shared space through masked attention and relative features. During training, we propose to let policy entropy identify uncertain agents, for which LaCAM3 provides confidence-triggered action interventions and label-smoothed imitation targets. During execution, a priority-aware PIBT module refines the proposed joint actions using persistent, learned, and distance-aware priorities together with policy-aware fallback preferences while maintaining collision-free execution. The resulting framework combines learned exploration with structured expert guidance without requiring LaCAM3 at inference. Experiments demonstrate that PRIMAL3 substantially outperforms state-of-the-art learning-based baselines and scales to ultra-large instances with up to city-level 100,000 agents. Real-world experiments further demonstrate the feasibility of deploying PRIMAL3 on physical robotic systems and ablation studies validate the individual contributions the components we proposed. Project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.04905 — 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 2026-10-31T11:39:29.946Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).