制御のための汎用ダイナミクスモデル
A Generalist Dynamics Model for Control
Transformerをダイナミクスモデルとして用い、未知環境への少数ショット・ゼロショット汎化性能を実証し、制御の基盤モデルとしての可能性を示した。
著者: Ingmar Schubert, Jingwei Zhang, Jake Bruce, Sarah Bechtle, Emilio Parisotto, Martin Riedmiller, Jost Tobias Springenberg, Arunkumar Byravan, Leonard Hasenclever, Nicolas Heess
分類: cs.AI, cs.RO
原文アブストラクト
We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, both in a few-shot setting, where a generalist TDM is fine-tuned with small amounts of data from the target environment, and in a zero-shot setting, where a generalist TDM is applied to an unseen environment without any further training. Here, we demonstrate that generalizing system dynamics can work much better than generalizing optimal behavior directly as a policy. Additional results show that TDMs also perform well in a single-environment learning setting when compared to a number of baseline models. These properties make TDMs a promising ingredient for a foundation model of control.
