SmolVLA
Hugging FaceOur current approach primarily relies on imitation learning.
general family · filed under post-training
Imitation learning trains a policy once, offline, rather than continually updating it via reinforcement learning.1 It learns high-performing policies from a fixed dataset of expert task demonstrations, without collecting new online interaction data.2
Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.
unlike other works that collect online interaction data to continually update specialist policies via reinforcement learning [19], here we focus on the simpler imitation learning paradigm— Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
we develop high-performing policies just by training once offline on a fixed dataset of expert task demonstrations— Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Also called Imitation learning for VLA training, imitation learning paradigm.
2 quotes from 2 sources, one card per model, each opening with its strongest.
Our current approach primarily relies on imitation learning.
we develop high-performing policies just by training once offline on a fixed dataset of expert task demonstrations