---
library_name: embryo_lab
tags:
  - robotics
  - reinforcement-learning
  - locomotion
  - isaac-lab
---

# XvKuoMing/embryo_lab-locomotion-spot-fast

A locomotion policy for **spot** (fast) trained with [embryo_lab](https://github.com/XvKuoMing/embryo_lab) on Isaac Lab task `Isaac-Velocity-Flat-Spot-v0` and exported to TorchScript.

## Deploy

Pull this checkpoint straight from the Hub -- no manual download:

```python
from embryo_lab import World
from embryo_lab.robots import Spot
from embryo_lab.skills import Locomotion

robot = Spot(locomotion=Locomotion("hub:spot/fast"))
with World(robot=robot) as world:
    robot.locomotion.move(vx=1.0)
    while world.is_running:
        world.step()
```

`Locomotion` reads the `metadata.json` deploy contract beside the policy and `World` auto-pins the physics rate to training, so it drives correctly with no tuning.

## Deploy contract (`metadata.json`)

- physics_dt: `0.002`  decimation: `10`  action_scale: `0.75`
- observation terms: `['base_lin_vel', 'base_ang_vel', 'projected_gravity', 'velocity_commands', 'joint_pos', 'joint_vel', 'actions']`