Glossary Entry

Vision-Language-Action Model

A robot policy built on a web-pretrained vision-language model, fine-tuned so that alongside understanding images and text it also outputs robot actions, either as discrete tokens or via a fast generative action head.

RL Models

Also called: VLA, VLAs, vision-language-action models

Seed source: Brohan et al., RT-2 (2023)

A vision-language-action model starts from a vision-language model that already carries web-scale knowledge about objects, scenes, and instructions, and teaches it to act: RT-2 coined the term by emitting discretized robot actions as text tokens, and later systems attach a small generative action expert that produces continuous action chunks at control rates.

The appeal is transfer: semantics learned from the internet (what a mug is, what “the extinct animal” refers to) show up in the robot’s behavior without robot data teaching them. Modern VLAs typically pair a slow, semantic backbone with a fast motor head (the System 2 / System 1 split) and are trained with the LLM-style ladder of pretraining, supervised fine-tuning on demonstrations, and increasingly reinforcement learning post-training.