iFaz/diff-aloha-policy-v4

DIFFUSION Policy — aloha_diff_baseline

Trained with LeRobot.
Date: 2026-06-03 08:08
Policy type: diffusion | Device: cuda

---

📦 Dataset

Parameter	Value
dataset.repo_id	lerobot/aloha_sim_transfer_cube_human

---

🏋️ Training Config

Parameter	Value
steps	5
batch_size	8
eval_freq	2
save_freq	2
num_workers	4
seed	42
eval.n_episodes	2
eval.batch_size	1

---

📐 Policy Architecture

All defaults — no overrides applied.

---

🎯 Eval Config

Parameter	Value
env.type	aloha
env.task	AlohaTransferCube-v0
eval.n_episodes	5
eval.batch_size	1
policy.path	/kaggle/working/outputs/train/aloha_diff_baseline/checkpoints/last/pretrained_model

---

📊 Eval Results

Metric	Value
Episodes	5
Success rate	0.0%
Avg sum reward	0.60
Avg max reward	0.60
Eval time (s)	1102.7

---

Citation

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