EQM Policy β eqm_aloha_transfer_cube_seed3_12sep2026_2pm
Trained with LeRobot.
Date: 2026-09-12 14:54
Policy type: eqm | Device: cuda
π¦ Dataset
| Parameter |
Value |
dataset.repo_id |
lerobot/aloha_sim_transfer_cube_human |
ποΈ Training Config
| Parameter |
Value |
steps |
5000 |
batch_size |
8 |
eval_freq |
0 |
save_freq |
1000 |
num_workers |
4 |
seed |
3 |
eval.n_episodes |
1 |
eval.batch_size |
1 |
eval.use_async_envs |
True |
π Policy Architecture
| Parameter |
Value |
ebm |
dot |
jacobian_reg_weight |
0.0001 |
jacobian_reg_probes |
1 |
π― Eval Config
| Parameter |
Value |
env.type |
aloha |
env.task |
AlohaTransferCube-v0 |
eval.n_episodes |
5 |
eval.batch_size |
1 |
eval.use_async_envs |
False |
policy.path |
/content/outputs/train/aloha_transfer_cube_seed3/checkpoints/last/pretrained_model |
policy.ood_logging_enabled |
True |
policy.ood_calibration_stats_path |
/kaggle/working/eqm_calibration.json |
policy.ood_log_path |
/kaggle/working/outputs/eqm_ood_log.csv |
policy.ood_z_threshold |
3.0 |
π Eval Results
| Metric |
Value |
| Episodes |
5 |
| Success rate |
0.0% |
| Avg sum reward |
0.40 |
| Avg max reward |
0.40 |
| Eval time (s) |
766.7 |
Citation
@misc{cadene2024lerobot,
author = {Cadene, Remi and Alibert, Simon and others},
title = {LeRobot},
year = {2024},
url = {https://github.com/huggingface/lerobot}
}