CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation
Chase McDonald, Cleotilde Gonzalez
TLDR
This paper introduces CoGrid and Multi-User Gymnasium, open-source tools for multi-agent human-AI interaction experiments, featuring simulations and web interfaces.
Key contributions
- CoGrid: A multi-agent grid-based simulation library with NumPy and JAX backends.
- Multi-User Gymnasium (MUG): Translates simulations into interactive web-based experiments.
- MUG supports arbitrary numbers of human and AI agents with robust networking (rollback netcode).
- Open-source tools designed to lower barriers for human-AI multi-agent experimentation.
Why it matters
Researchers lack accessible tools for human-AI multi-agent experiments. This paper introduces CoGrid and MUG, open-source frameworks that reduce these barriers. They enable studies into social decision-making, psychology, and cognition related to human-AI interaction.
Original Abstract
The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and questions for regarding how humans interact with autonomous agents. Multi-agent experiments, where humans and AI act together, can offer important opportunities to study social decision making, but there is a lack of accessible tooling available to researchers to run such experiments. We introduce two tools designed to reduce these barriers. The first, CoGrid, is a multi-agent grid-based simulation library with dual NumPy and JAX backends. The second, Multi-User Gymnasium (MUG), translates such simulation environments directly into interactive web-based experiments. MUG supports interactions with arbitrary numbers of humans and AI, utilizing either server-authoritative or peer-to-peer networking with rollback netcode to account for latency. Together, these tools can enable researchers to deploy studies of human-AI interaction, facilitating inquiry into core questions of psychology, cognition, and decision making and their relationship to human-AI interaction. Both tools are open source and available to the broader research community. Documentation and source code is available at {cogrid, multi-user-gymnasium}.readthedocs.io. This paper details the functionality of these tools and presents several case studies to illustrate their utility in human-AI multi-agent experimentation.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.