Modelpublic

iFaz/eqm-pusht-seed3-21sep2026_8am

sourceHugging Faceapache-2.0updated 6d agoView on Hugging Face

0likes34downloads

Model Card

EQM Policy — eqmpushtseed321sep20268am

Trained with LeRobot. Date: 2026-09-21 09:11 Policy type: eqm | Device: cuda

📦 Dataset

Parameter	Value
`dataset.repo_id`	`lerobot/pusht`

🏋️ Training Config

Parameter	Value
`steps`	`10000`
`batch_size`	`8`
`eval_freq`	`0`
`save_freq`	`5000`
`num_workers`	`4`
`seed`	`3`
`eval.n_episodes`	`1`
`eval.batch_size`	`1`
`eval.use_async_envs`	`True`

📐 Policy Architecture

Parameter	Value
`jacobian_reg_weight`	`0.001`
`jacobian_reg_probes`	`1`
`fixed_point_anchor_weight`	`0.1`
`c_gamma_a`	`0.5`
`use_adaptive_compute`	`False`

🎯 Eval Config

Parameter	Value
`env.type`	`pusht`
`env.task`	`PushT-v0`
`eval.n_episodes`	`100`
`eval.batch_size`	`1`
`eval.use_async_envs`	`False`
`policy.path`	`/content/outputs/train/pusht_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`

📊 Eval Results

Metric	Value
Episodes	`100`
Success rate	`1.0%`
Avg sum reward	`14.14`
Avg max reward	`0.27`
Eval time (s)	`1474.4`

Citation

bibtex

@misc{cadene2024lerobot,
  author = {Cadene, Remi and Alibert, Simon and others},
  title  = {LeRobot},
  year   = {2024},
  url    = {https://github.com/huggingface/lerobot}
}