Instructions to use Autobrik/SO-ARM100-dump-pocket-cleaning2-act with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Autobrik/SO-ARM100-dump-pocket-cleaning2-act with LeRobot:
- Notebooks
- Google Colab
- Kaggle
ACT finetuned on SO-ARM100 dump-pocket-cleaning
This is an ACT policy finetuned with LeRobot.
Training summary
- policy:
act - dataset:
Autobrik/SO-ARM100-dump-pocket-cleaning2 - run_dir:
outputs/train/benchmark/20260215_071412_benchmark_act - seed:
1000
Best offline validation
- best_val_step:
N/A - best_val_loss:
0.27459109516460034
Included artifacts
checkpoints/best(recommended for eval/deploy)checkpoints/last(resume/debug)best_val.json