Norsk(NO) Solving Multi-Agent Sokoban via LaCAM

新规划器应对复杂的多智能体 Sokoban 挑战

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-30 14:57

研究人员开发了一种名为 Sokoban-LaCAM 的新规划器，能够高效地解决多智能体 Sokoban 游戏实例，该游戏涉及智能体推动箱子到目标位置。该方法利用了多智能体路径查找 (MAPF) 的最新进展，以处理多智能体带来的复杂性，例如增加的分支因子以及集成任务分配和无碰撞路径查找的需求。Sokoban-LaCAM 规划器通过成功管理数十个智能体和箱子，同时保持完整性和最终最优性，展示了其可扩展性，这表明 MAPF 可用于更广泛的集体自动化挑战。 AI

影响为多智能体系统引入了一种可扩展的规划方法，可能适用于物流和其他自动化任务。

排序理由学术论文，详细介绍了一种解决复杂规划问题的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种解决复杂规划问题的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 6 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.MA (Multiagent) TIER_1 Norsk(NO) · Keisuke Okumura · 2026-09-30 14:57

通过 LaCAM 解决多智能体 Sokoban 问题

Sokoban, a puzzle game in which an agent pushes boxes onto unlabelled target locations in a grid world, is a long-standing benchmark planning problem. While it is easy to see the connection to practical applications such as warehouse logistics with autonomous forklifts, its multi…

本文如何被排名

报道来源 [1]

通过 LaCAM 解决多智能体 Sokoban 问题

相关实体

相关话题