インスタントポリシー:グラフ拡散による文脈内模倣学習
Instant Policy: In-Context Imitation Learning via Graph Diffusion
実演1〜2回から新しいタスクを即座に学習する文脈内模倣学習手法を提案し、グラフ表現と拡散モデルで実演・観測・行動を構造的に推論する。
著者: Vitalis Vosylius, Edward Johns
分類: cs.RO, cs.AI, cs.CV, cs.LG
原文アブストラクト
Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly (without further training) from just one or two demonstrations, achieving ICIL through two key components. First, we introduce inductive biases through a graph representation and model ICIL as a graph generation problem with a learned diffusion process, enabling structured reasoning over demonstrations, observations, and actions. Second, we show that such a model can be trained using pseudo-demonstrations - arbitrary trajectories generated in simulation - as a virtually infinite pool of training data. Simulated and real experiments show that Instant Policy enables rapid learning of various everyday robot tasks. We also show how it can serve as a foundation for cross-embodiment and zero-shot transfer to language-defined tasks. Code and videos are available at https://www.robot-learning.uk/instant-policy.
