SOURCE-LINKED INTELLIGENCE

Behavior-Aligned Action Tokenization for Robot Policy Learning

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Autoregressive robot policies learn continuous control by predicting discrete action tokens from observations. Different tasks often share local motions, yet behavioral correspondence across demonstrations receives limited explicit supervision in existing tokenizers. Motions with different timing can therefore lack a shared representation despite following similar patterns. We propose Behavior-Aligned Action Tokenization (BAAT), which uses soft dynamic time warping (Soft-DTW) to select corresponding action chunks and aligns their quantized coordinates jointly with reconstruction. This objectiv

Read original source ↗ Open in workspace

recordType

paper

region

Global