EQM Policy β€” eqm_aloha_transfer_cube_seed3_12sep2026_2pm

Trained with LeRobot.
Date: 2026-09-12 14:54
Policy type: eqm | Device: cuda


πŸ“¦ Dataset

Parameter Value
dataset.repo_id lerobot/aloha_sim_transfer_cube_human

πŸ‹οΈ 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

πŸ“ Policy Architecture

Parameter Value
ebm dot
jacobian_reg_weight 0.0001
jacobian_reg_probes 1

🎯 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

πŸ“Š 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}
}
Downloads last month
30
Safetensors
Model size
18.7M params
Tensor type
F32
Β·
Video Preview
loading

Dataset used to train iFaz/eqm-aloha_transfer_cube-seed3-12sep2026_2pm