Mini Diffuser: 二段階ミニバッチによる高速マルチタスク拡散ポリシー学習
Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batches
拡散ポリシー学習において、視覚言語条件ごとに複数のノイズ付き行動サンプルを組み合わせる二段階ミニバッチを導入し、情報漏洩を防ぐアーキテクチャ改良により、性能を保ちつつ学習時間とメモリを大幅に削減した。
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: Yutong Hu, Pinhao Song, Kehan Wen, Renaud Detry
分類: cs.RO, cs.LG
原文アブストラクト
We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from a previously underexplored distinction between action diffusion and the image diffusion techniques that inspired it: In image generation, the target is high-dimensional. By contrast, in action generation, the dimensionality of the target is comparatively small, and only the image condition is high-dimensional. Our approach, \emph{Mini Diffuser}, exploits this asymmetry by introducing \emph{two-level minibatching}, which pairs multiple noised action samples with each vision-language condition, instead of the conventional one-to-one sampling strategy. To support this batching scheme, we introduce architectural adaptations to the diffusion transformer that prevent information leakage across samples while maintaining full conditioning access. In RLBench simulations, Mini-Diffuser achieves 95\% of the performance of state-of-the-art multi-task diffusion policies, while using only 5\% of the training time and 7\% of the memory. Real-world experiments further validate that Mini-Diffuser preserves the key strengths of diffusion-based policies, including the ability to model multimodal action distributions and produce behavior conditioned on diverse perceptual inputs. Code available at mini-diffuse-actor.github.io
