Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO

We present the results of the second Neural MMO challenge, hosted at IJCAI 2022, which received 1600+ submissions. This competition targets robustness and generalization in multi-agent systems: participants train teams of agents to complete a multi-task objective against opponents not seen during tr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yangkun, Suarez, Joseph, Zhang, Junjie, Yu, Chenghui, Wu, Bo, Chen, Hanmo, Zhu, Hengman, Du, Rui, Qian, Shanliang, Liu, Shuai, Hong, Weijun, He, Jinke, Zhang, Yibing, Zhao, Liang, Zhu, Clare, Togelius, Julian, Mohanty, Sharada, Chen, Jiaxin, Li, Xiu, Zhu, Xiaolong, Isola, Phillip
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present the results of the second Neural MMO challenge, hosted at IJCAI 2022, which received 1600+ submissions. This competition targets robustness and generalization in multi-agent systems: participants train teams of agents to complete a multi-task objective against opponents not seen during training. The competition combines relatively complex environment design with large numbers of agents in the environment. The top submissions demonstrate strong success on this task using mostly standard reinforcement learning (RL) methods combined with domain-specific engineering. We summarize the competition design and results and suggest that, as an academic community, competitions may be a powerful approach to solving hard problems and establishing a solid benchmark for algorithms. We will open-source our benchmark including the environment wrapper, baselines, a visualization tool, and selected policies for further research.
DOI:10.48550/arxiv.2308.15802