Ad-Hoc Human-AI Coordination Challenge

TL;DR

This paper introduces the AH2AC2 challenge for human-AI coordination using Hanabi, developing human proxy agents for scalable evaluation, and providing baseline results with open datasets and controlled evaluation systems.

Contribution

It presents a novel benchmark for human-AI coordination in Hanabi, with human proxy agents and a large dataset to facilitate research and reproducibility.

Findings

Developed human proxy agents for Hanabi coordination evaluation.

Open-sourced a dataset of 3,079 games for research.

Provided baseline results for two- and three-player scenarios.

Abstract

Achieving seamless coordination between AI agents and humans is crucial for real-world applications, yet it remains a significant open challenge. Hanabi is a cooperative card game featuring imperfect information, constrained communication, theory of mind requirements, and coordinated action -- making it an ideal testbed for human-AI coordination. However, its use for human-AI interaction has been limited by the challenges of human evaluation. In this work, we introduce the Ad-Hoc Human-AI Coordination Challenge (AH2AC2) to overcome the constraints of costly and difficult-to-reproduce human evaluations. We develop \textit{human proxy agents} on a large-scale human dataset that serve as robust, cheap, and reproducible human-like evaluation partners in AH2AC2. To encourage the development of data-efficient methods, we open-source a dataset of 3,079 games, deliberately limiting the amount of available human gameplay data. We present baseline results for both two- and three- player Hanabi scenarios. To ensure fair evaluation, we host the proxy agents through a controlled evaluation system rather than releasing them publicly. The code is available at \href{https://github.com/FLAIROx/ah2ac2}{https://github.com/FLAIROx/ah2ac2}.