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.
翻译:我们介绍POGEMA(https://github.com/AIRI-Institute/pogema)一个沙箱,用来挑战部分可见的多试剂路由(PO-MAPF)问题。这是一个基于网格的环境,专门设计成一个灵活、可捕捉和可扩缩的基准。它可以适合各种PO-MAPF,它可以作为规划和学习方法的极好测试场,并且可以结合起来,使我们能够缩小AI规划和学习之间的差距。