arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.03634cs.ROcs.GTcs.LGcs.MA
收藏

基于优先级通信学习的多Agent路径搜索

Multi-Agent Path Finding with Prioritized Communication Learning

East China Normal University(华东师范大学);Geekplus Technology Co., Ltd.(极智嘉科技股份有限公司);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Wenhao Li, Hongjun Chen, Bo Jin, Wenzhe Tan, Hongyuan Zha, Xiangfeng Wang

摘要:

多智能体寻路(MAPF)已被广泛用于解决大规模的现实世界的问题,例如,自动化仓库基于学习的,完全分散的框架已被引入,以减轻实时问题,同时追求最佳的规划政策。然而,现有的方法可能会产生显着更多的顶点冲突(或碰撞),这导致低成功率或更多的完工时间。在本文中,我们提出了一个优先通信学习方法(PICO),它将\textit{implicit}规划优先级到通信拓扑结构内的分散多智能体强化学习框架。隐式优先级学习模块与经典的耦合规划器相结合,形成动态的通信拓扑,并建立有效的冲突避免机制。PICO在大规模MAPF任务中的成功率和碰撞率明显优于最先进的基于学习的规划器。

英文摘要:

Multi-agent pathfinding (MAPF) has been widely used to solve large-scale real-world problems, e.g., automation warehouses. The learning-based, fully decentralized framework has been introduced to alleviate real-time problems and simultaneously pursue optimal planning policy. However, existing methods might generate significantly more vertex conflicts (or collisions), which lead to a low success rate or more makespan. In this paper, we propose a PrIoritized COmmunication learning method (PICO), which incorporates the \textit{implicit} planning priorities into the communication topology within the decentralized multi-agent reinforcement learning framework. Assembling with the classic coupled planners, the implicit priority learning module can be utilized to form the dynamic communication topology, which also builds an effective collision-avoiding mechanism. PICO performs significantly better in large-scale MAPF tasks in success rates and collision rates than state-of-the-art learning-based planners.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑