arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.06148cs.LGcs.AI
收藏

部分可观测网格环境下多Agent路径发现的Q-混合网络

Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments

Moscow Institute of Physics and Technology(莫斯科物理技术学院);Moscow Aviation Institute(莫斯科航空学院);Artificial Intelligence Research Institute FRC CSC RAS(俄罗斯科学院联邦科学研究中心计算机科学与控制研究所人工智能研究院)

Vasilii Davydov, Alexey Skrynnik, Konstantin Yakovlev, Aleksandr I. Panov

摘要:

在本文中,我们考虑在部分可观测网格环境中的多智能体导航问题。这个问题对于集中式规划方法来说是具有挑战性的,因为它们通常依赖于对环境的全面了解。我们建议利用强化学习的方法时,代理,首先,学习的政策,映射观察到的行动,然后遵循这些政策,以达到他们的目标。为了解决与学习合作行为相关的挑战,即在许多情况下,代理需要相互让步以完成任务,我们使用混合Q网络来补充学习个体策略。在实验评估中,我们表明,这种方法导致合理的结果和规模以及大量的代理。

英文摘要:

In this paper, we consider the problem of multi-agent navigation in partially observable grid environments. This problem is challenging for centralized planning approaches as they, typically, rely on the full knowledge of the environment. We suggest utilizing the reinforcement learning approach when the agents, first, learn the policies that map observations to actions and then follow these policies to reach their goals. To tackle the challenge associated with learning cooperative behavior, i.e. in many cases agents need to yield to each other to accomplish a mission, we use a mixing Q-network that complements learning individual policies. In the experimental evaluation, we show that such approach leads to plausible results and scales well to large number of agents.

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。

↑