Open Models Almanac
Methodspost-training

general family · filed under post-training

Pre-training followed by post-training for robot policies

A two-stage robot-policy recipe that first adapts the model through pre-training and then specializes it through post-training.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See post-training for the methods filed beside it.

Also called a multi-stage training procedure, Two-stage pre-training and post-training, two-stage training recipe, two stages.

sources
3
models
2
labs adopt it
2
strongest
core

Documented in

Physical Intelligence

Evidence

3 quotes from 3 sources, one card per model, each opening with its strongest.

How sources treat it
core 3

π0.5

Physical Intelligenceadopted2 sources

training then proceeds in two stages: a pre-training stage intended to adapt the model to diverse robotic tasks, and a post-training stage intended to specialize it to mobile manipulation

coreunclearin π0.5
1 more from this model

we employ a multi-stage training procedure for our model.

coreunclearin π0Physical Intelligence
↑