Author

Arrasy Rahman

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

JaxAHT: A JAX-Based Library for Ad Hoc Teamwork

JaxAHT is introduced, the first open-source, JAX-based library designed to accelerate and standardize the AHT research lifecycle and provides a unified framework for teammate generation, ego agent training, and evaluation against unseen teammates, achieving approximately 95x wall-clock speedup over PyTorch counterparts...

Caroline Wang, Rolando Fernandez, Z. Mustafaoglu et al. · 2 citations

#artificial intelligence May 2025

ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork

ROTATE is introduced, a regret-driven, open-ended training algorithm that alternates between improving the AHT agent and generating teammates that probe its collaboration deficiencies, establishing a new standard for robust, generalizable teamwork.

Caroline Wang, Arrasy Rahman, Jia-Xun Cui et al. · arXiv.org · 8 citations · ⚡1