Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari

ArXi:2605.08578v1 Announce Type: cross Developing generalist systems that retain human-like data efficiency is a central challenge. While world models (WMs) offer a promising path, existing research often conflates architectural mechanisms with the independent impact of model \emph{scale}. In this work, we use a minimalist transformer world model to analyze scaling behaviors on the Atari 100k benchmark, using fixed offline datasets derived from a presupposed expert policy.