Learning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action Models
[Widzenie komputerowe] Autorzy: Qi Lyu, Jiahua Dong, Hao Shen i 9 więcej
World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience across manipulation tasks. Furthermore, existing WAMs struggle to capture underlying cross-task semantic relationships that could guide target action prediction, as redundant background elements interfere with the extraction of key visual information. To address these challenges, we develop a novel Action Experience Dictionary (AED) that encodes historical physical action trajectories into shared action embeddings to support skill reuse and model cross-task relationships. Specifically, we first aggregate historical actions to align with visual observations and retrieve action embeddings from the AED using a pretrained action tokenizer. Subsequently, we visually condition the pooled embeddings through cross-attention and prepend them to no…
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe