Fine-tuning Policies
Fine-tuning policies with fresh demonstrations that you have collected.
Last updated
Fine-tuning policies with fresh demonstrations that you have collected.
Last updated
The following assumes that the current working directory is this repository’s root folder.
Modify include_task
and include_env
in finetune.yaml
depending on the task and env you intend to finetune.
[Optional, non-default:] only if you're using torch encoder, set enc_weight_pth
(path to pretrained encoder weights) in image_bc_depth.yaml
. You can download the weights from if you don't have them.
Run in terminal:
[Optional, experimental] If you want to take advantage of multi-GPU training using 🤗 accelerate, you can use the following command: