実世界動画による文脈化ワールドモデルの事前学習と強化学習への応用
Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
実世界の多様な動画から文脈とダイナミクスを分離して学習するContextWMを提案し、ロボット操作・歩行・自動運転などの視覚制御タスクにおけるモデルベース強化学習のサンプル効率を大幅に改善した。
著者: Jialong Wu, Haoyu Ma, Chaoyi Deng, Mingsheng Long
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Unsupervised pre-training methods utilizing large and diverse datasets have achieved tremendous success across a range of domains. Recent work has investigated such unsupervised pre-training methods for model-based reinforcement learning (MBRL) but is limited to domain-specific or simulated data. In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of downstream visual control tasks. However, in-the-wild videos are complicated with various contextual factors, such as intricate backgrounds and textured appearance, which precludes a world model from extracting shared world knowledge to generalize better. To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes. Specifically, a contextualized extension of the latent dynamics model is elaborately realized by incorporating a context encoder to retain contextual information and empower the image decoder, which encourages the latent dynamics model to concentrate on essential temporal variations. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of MBRL in various domains, including robotic manipulation, locomotion, and autonomous driving. Code is available at this repository: https://github.com/thuml/ContextWM.
