---
datasets:
- lerobot/pusht
language: en
library_name: lerobot
license: apache-2.0
tags:
- robotics
- imitation-learning
- diffusion
- mujoco
- pytorch_model_hub_mixin
---

# DIFFUSION Policy — diffusion_pusht_seed3

Trained with [LeRobot](https://github.com/huggingface/lerobot).  
Date: `2026-05-29 02:01`  
Policy type: `diffusion` | Device: `cuda`

---

## 📦 Dataset

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

---

## 🏋️ Training Config

| Parameter | Value |
|---|---|
| `steps` | `70000` |
| `batch_size` | `8` |
| `eval_freq` | `0` |
| `save_freq` | `20000` |
| `num_workers` | `4` |
| `seed` | `3` |
| `eval.n_episodes` | `1` |
| `eval.batch_size` | `1` |
| `eval.use_async_envs` | `True` |

---

## 📐 Policy Architecture

| Parameter | Value |
|---|---|
| `noise_scheduler_type` | `DDIM` |
| `num_inference_steps` | `15` |

---

## 🎯 Eval Config

| Parameter | Value |
|---|---|
| `env.type` | `pusht` |
| `env.task` | `PushT-v0` |
| `eval.n_episodes` | `8` |
| `eval.batch_size` | `4` |
| `eval.use_async_envs` | `False` |
| `policy.path` | `/kaggle/working/outputs/train/pusht_seed3/checkpoints/last/pretrained_model` |

---

## 📊 Eval Results

| Metric | Value |
|---|---|
| Episodes | `8` |
| Success rate | `12.5%` |
| Avg sum reward | `84.67` |
| Avg max reward | `0.66` |
| Eval time (s) | `48.2` |

---

## Citation

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