论文标题
Pogema：多种代理的部分可观察的网格环境
POGEMA: Partially Observable Grid Environment for Multiple Agents
论文作者
论文摘要
我们介绍了Pogema（https://github.com/airi-institute/pogema）一个沙盒，用于挑战部分可观察到的多代理探路（PO-MAPF）问题。这是一个基于网格的环境，专门设计为灵活，可调和可扩展的基准。它可以针对各种PO-MAPF量身定制，该PO-MAPF可以作为规划和学习方法的绝佳测试场，以及它们的组合，这将使我们能够填补AI计划和学习之间的差距。
We introduce POGEMA (https://github.com/AIRI-Institute/pogema) a sandbox for challenging partially observable multi-agent pathfinding (PO-MAPF) problems . This is a grid-based environment that was specifically designed to be a flexible, tunable and scalable benchmark. It can be tailored to a variety of PO-MAPF, which can serve as an excellent testing ground for planning and learning methods, and their combination, which will allow us to move towards filling the gap between AI planning and learning.
