Multi-agent reinforcement learning (MARL) has recently excelled in solving challenging cooperative and competitive multi-agent problems in various environments, typically involving a small number of agents and full observability. Moreover, a range of crucial robotics-related tasks, such as multi-robot pathfinding, which have traditionally been approached with classical non-learnable methods (e.g., heuristic search), are now being suggested for solution using learning-based or hybrid methods. However, in this domain, it remains difficult, if not impossible, to conduct a fair comparison between classical, learning-based, and hybrid approaches due to the lack of a unified framework that supports both learning and evaluation. To address this, we introduce POGEMA, a comprehensive set of tools that includes a fast environment for learning, a problem instance generator, a collection of predefined problem instances, a visualization toolkit, and a benchmarking tool for automated evaluation. We also introduce and define an evaluation protocol that specifies a range of domain-related metrics, computed based on primary evaluation indicators (such as success rate and path length), enabling a fair multi-fold comparison. The results of this comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented.
DOI: 10.48550/arXiv.2407.14931
Скачать статью (PDF) из архива arXiv.org (англ.): https://arxiv.org/html/2407.14931v1
Скачать статью (PDF) из архива конференции на OpenView (англ.): https://openreview.net/forum?id=6VgwE2tCRm
ResearchGate: https://www.researchgate.net/publication/382459974_POGEMA_A_Benchmark_Platform_for_Cooperative_Multi-Agent_Navigation
Alexey Skrynnik, Anton Andreychuk, Anatolii Borzilov, Alexander Chernyavskiy, Konstantin Yakovlev, Aleksandr Panov. POGEMA: A Benchmark Platform for Cooperative Multi-Agent Navigation // The Thirteenth International Conference on Learning Representations ICLR 2025, Singapore EXPO, Thu Apr 24 – Mon Apr 28th, 2025.