POGEMA: Partially Observable Grid Environment for Multiple Agents
This provides a tunable benchmark for researchers working on PO-MAPF, though it is incremental as it builds on existing environment frameworks.
The authors introduced POGEMA, a flexible and scalable grid-based sandbox environment designed to benchmark partially observable multi-agent pathfinding (PO-MAPF) problems, aiming to bridge the gap between AI planning and learning methods.
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.