search

mateuszwyszynski / octo

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
https://octo-models.github.io/
MIT License
0 stars 0 forks source link

3 eval and train data format mismatch #4

Closed mateuszwyszynski closed 2 weeks ago

mateuszwyszynski commented 3 weeks ago

This should fix the mismatch between proprio state data values during training and evaluation. Code to generate the single examples for which one can easily compare the values can be found in the corresponding issue

mateuszwyszynski commented 2 weeks ago

This also solves #2