MoVie: 視点汎化のための視覚モデルベース方策適応
MoVie: Visual Model-Based Policy Adaptation for View Generalization
視覚強化学習エージェントが未知の視点に適応できるよう、テスト時に報酬信号なしでモデルベース方策を適応させる手法を提案し、18タスクで大幅な性能向上を達成した。
著者: Sizhe Yang, Yanjie Ze, Huazhe Xu
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
Visual Reinforcement Learning (RL) agents trained on limited views face significant challenges in generalizing their learned abilities to unseen views. This inherent difficulty is known as the problem of $\textit{view generalization}$. In this work, we systematically categorize this fundamental problem into four distinct and highly challenging scenarios that closely resemble real-world situations. Subsequently, we propose a straightforward yet effective approach to enable successful adaptation of visual $\textbf{Mo}$del-based policies for $\textbf{Vie}$w generalization ($\textbf{MoVie}$) during test time, without any need for explicit reward signals and any modification during training time. Our method demonstrates substantial advancements across all four scenarios encompassing a total of $\textbf{18}$ tasks sourced from DMControl, xArm, and Adroit, with a relative improvement of $\mathbf{33}$%, $\mathbf{86}$%, and $\mathbf{152}$% respectively. The superior results highlight the immense potential of our approach for real-world robotics applications. Videos are available at https://yangsizhe.github.io/MoVie/ .
