JaxAHT: A JAX-Based Library for Ad Hoc Teamwork
Lists
Only you see this
Abstract
Ad Hoc Teamwork (AHT) addresses the challenge of designing agents capable of coordinating with novel partners without prior coordination. However, progress in the field is hindered by the prohibitive computational cost of the AHT research lifecycle, the lack of standardized benchmark implementations, and the absence of a diverse, validated evaluation teammate suite. In this work, we introduce JaxAHT, the first open-source, JAX-based library designed to accelerate and standardize the AHT research lifecycle. Leveraging JAX's hardware acceleration and massive parallelization capabilities, JaxAHT provides a unified framework for teammate generation, ego agent training, and evaluation against unseen teammates, achieving approximately 95x wall-clock speedup over PyTorch counterparts. Alongside the library, we contribute a diverse suite of evaluation teammates across the domains of Level-Based Foraging, Overcooked, and Hanabi. To illustrate the value of the framework, we use it to conduct a large-scale, compute-controlled benchmark study comparing teammate generation and AHT agent learning methods, finding that no algorithm consistently performs best, and that agent modeling primarily offers benefits in role-based scenarios with diverse teammates.
BibTeX
@inproceedings{wang2026jaxaht,
author = {Caroline Wang and Rolando Fernandez and Zelal Su Mustafaoglu and Montek Kundan and Jiaxun Cui and Lingyun Xiao and Zhihan Wang and Di Yang Shi and Aditya Madhan and Johnny Liu and Arrasy Rahman and Peter Stone},
title = {{JaxAHT: A JAX-Based Library for Ad Hoc Teamwork}},
booktitle = {MALGAI @ ICLR},
year = {2026},
url = {https://openreview.net/forum?id=DkZ2IEBpH1},
}Loading related content...