---
datasets: BrianZhengJourney/libero_bowl_sarm
library_name: lerobot
license: apache-2.0
model_name: sarm
pipeline_tag: robotics
tags:
- robotics
- reward-model
- sarm
- lerobot
---

# Reward Model Card for sarm

<!-- Provide a quick summary of what the reward model is/does. -->


A Success-Aware Reward Model (SARM) predicts a dense reward signal from observations, typically used downstream for reinforcement learning or human-in-the-loop fine-tuning when task success is not directly observable.


This reward model has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).

---

## How to Get Started with the Reward Model

### Train from scratch

```bash
lerobot-train \
  --dataset.repo_id=${HF_USER}/<dataset> \
  --reward_model.type=sarm \
  --output_dir=outputs/train/<desired_reward_model_repo_id> \
  --job_name=lerobot_reward_training \
  --reward_model.device=cuda \
  --reward_model.repo_id=${HF_USER}/<desired_reward_model_repo_id> \
  --wandb.enable=true
```

_Writes checkpoints to `outputs/train/<desired_reward_model_repo_id>/checkpoints/`._

### Load the reward model in Python

```python
from lerobot.rewards import make_reward_model

reward_model = make_reward_model(pretrained_path="<hf_user>/<reward_model_repo_id>")
reward = reward_model.compute_reward(batch)
```

---

## Model Details

- **License:** apache-2.0