Atariにおけるデータ効率的な汎用トランスフォーマーワールドモデルに対するスケールの影響の調査
Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari
Atari 100kベンチマークで、最小限のトランスフォーマーワールドモデルを用いて、モデル規模が環境ごとに異なるスケーリング挙動を示すことを明らかにし、統合トレーニングがスケーリングダイナミクスを安定化させることを実証した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Jooyeon Kim
分類: cs.LG, cs.AI
原文アブストラクト
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. Our results reveal that environments fundamentally fall into distinct scaling regimes, even when constrained by identical offline data budgets and model capacities. For individual tasks, some environments naturally allow models to pass the interpolation threshold, yielding monotonic improvements in the overparameterized regime, while others remain trapped in the classical regime, where larger world models degrade fidelity. In the unified setting, i.e., a single transformer trained on a suite of 26 Atari environments, we uncover that joint training stabilizes scaling dynamics, ensuring monotonic gains across all environments, regardless of their distinct inherent scaling regimes. Finally, we demonstrate that improved fidelity translates directly to downstream control, with policies learned entirely within the simulated dynamics achieving a median expert-random-normalized score of 0.770. Our findings suggest that future progress lies as much in precise scaling strategies as in architectural innovation.
