mlsanityData to 14 Oct 2026

CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation

arXiv 2604.15044 ↗First posted 16 Apr 2026cs.HC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

20 of 44 references.

References · 20

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  4. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  5. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  6. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 209
  7. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
  8. 2021Collaborating with Humans without Human Datacited by 142
  9. 2022Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learningcited by 131
  10. 2020Learning to Complement Humanscited by 124
  11. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  12. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
8 more
  1. 2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 97
  2. 2023JaxMARL: Multi-Agent RL Environments and Algorithms in JAXcited by 63
  3. 2022Melting Pot 2.0cited by 40
  4. 2020Griddly: A platform for AI research in gamescited by 31
  5. 2024NAVIX: Scaling MiniGrid Environments with JAXcited by 18
  6. 2022POGEMA: Partially Observable Grid Environment for Multiple Agentscited by 6
  7. 2015MazeBase: A Sandbox for Learning from Gamescited by 4
  8. 2025SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experimentscited by 1

Built on by

Not cited yet.