Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Continuous action representation

A continuous action representation lets a VLA model output actions directly as continuous values instead of discretizing them into bins.1 It avoids the discretization dilemma where finer bins improve precision but make individual tokens rarer in training data, hurting generalization.2

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. with a continuous action representation, the VLA can directly model the action distribution without lossy discretization — Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
  2. increasing the number of bins used for discretization improves precision but reduces the frequency of individual tokens in the training data, potentially hurting generalization — Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Also called continuous action representations.

Filed under model architecture › multimodal architecture