VAMPO: ビデオ行動モデルの視覚ダイナミクスを改善するポリシー最適化
VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models
ビデオ行動モデルのノイズ除去を逐次決定過程とみなし、専門家の視覚ダイナミクスに基づく報酬でポリシー最適化を行うことで、操作に重要な視覚ダイナミクスを直接改善するフレームワークを提案。
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: Zirui Ge, Pengxiang Ding, Baohua Yin, Qishen Wang, Zhiyong Xie, Yemin Wang, Jinbo Wang, Hengtao Li, Runze Suo, Wenxuan Song, Han Zhao, Shangke Lyu, Zhaoxin Fan, Haoang Li, Ran Cheng, Cheng Chi, Huibin Ge, Yaozhi Luo, Donglin Wang
分類: cs.RO
原文アブストラクト
Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based video predictors are trained with likelihood-surrogate objectives, which encourage globally plausible predictions without explicitly optimizing the precision-critical visual dynamics needed for manipulation. This objective mismatch often leads to subtle errors in object pose, spatial relations, and contact timing that can be amplified by downstream policies. We propose VAMPO, a post-training framework that directly improves visual dynamics in video action models through policy optimization. Our key idea is to formulate multi-step denoising as a sequential decision process and optimize the denoising policy with rewards defined over expert visual dynamics in latent space. To make this optimization practical, we introduce an Euler Hybrid sampler that injects stochasticity only at the first denoising step, enabling tractable low-variance policy-gradient estimation while preserving the coherence of the remaining denoising trajectory. We further combine this design with GRPO and a verifiable non-adversarial reward. Across diverse simulated and real-world manipulation tasks, VAMPO improves task-relevant visual dynamics, leading to better downstream action generation and stronger generalization. The homepage is https://vampo-robot.github.io/VAMPO/.
