arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02373cs.ROcs.MA
收藏

编队向前移动：多智能体协同移动的分散分层学习方法

Moving Forward in Formation: A Decentralized Hierarchical Learning Approach to Multi-Agent Moving Together

Zhejiang University（浙江大学）

Shanqi Liu, Licheng Wen, Jinhao Cui, Xuemeng Yang, Junjie Cao, Yong Liu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

多智能体信息寻路具有许多潜在的实际应用，如移动仓库机器人。然而，以前的多智能体路径搜索（MAPF）方法很少考虑编队。此外，它们通常是集中式规划者，需要了解整个环境状况。MAPF的其他分散的部分可观察方法是强化学习（RL）方法。然而，这些强化学习方法在同时学习路径发现和编队问题时遇到困难。在本文中，我们提出了一种新的分散的部分可观察的RL算法，使用分层结构分解成不相关的多目标任务。该方法还计算了一个理论权重，使得每个任务的奖励对最终RL价值函数的影响相等。此外，我们引入了一种通信方法，帮助代理相互合作。仿真实验表明，我们的方法优于其他端到端的强化学习方法，我们的方法可以自然地扩展到大的世界规模，集中式规划器的斗争。我们还部署和验证我们的方法在现实世界的情况下。

英文摘要：

Multi-agent path finding in formation has many potential real-world applications like mobile warehouse robots. However, previous multi-agent path finding (MAPF) methods hardly take formation into consideration. Furthermore, they are usually centralized planners and require the whole state of the environment. Other decentralized partially observable approaches to MAPF are reinforcement learning (RL) methods. However, these RL methods encounter difficulties when learning path finding and formation problem at the same time. In this paper, we propose a novel decentralized partially observable RL algorithm that uses a hierarchical structure to decompose the multi objective task into unrelated ones. It also calculates a theoretical weight that makes every task reward has equal influence on the final RL value function. Additionally, we introduce a communication method that helps agents cooperate with each other. Experiments in simulation show that our method outperforms other end-to-end RL methods and our method can naturally scale to large world sizes where centralized planner struggles. We also deploy and validate our method in a real world scenario.

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。

↑