---
license: mit
library_name: pytorch
tags:
  - reinforcement-learning
  - locomotion
  - robotics
  - g1
---

# g1-fight

PyTorch checkpoint for a G1 humanoid locomotion policy trained with
ADD (Adversarial Differential of Discriminators).

## Checkpoint info

| Key | Value |
|-----|-------|
| Training iterations | `8,900` |
| Total environment samples | `4,666,687,488` |
| Number of parameters | `1,983,104` |

## Usage

```python
import torch

checkpoint = torch.load("model.pt", map_location="cpu")
state_dict = checkpoint["model"]
# Load into your agent:
# agent.load_state_dict(state_dict)
```