English

POGEMA: Partially Observable Grid Environment for Multiple Agents

Machine Learning 2022-06-23 v1 Artificial Intelligence Multiagent Systems

Abstract

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.

Keywords

Cite

@article{arxiv.2206.10944,
  title  = {POGEMA: Partially Observable Grid Environment for Multiple Agents},
  author = {Alexey Skrynnik and Anton Andreychuk and Konstantin Yakovlev and Aleksandr I. Panov},
  journal= {arXiv preprint arXiv:2206.10944},
  year   = {2022}
}

Comments

7 pages, 7 figures

R2 v1 2026-06-24T11:59:49.442Z