> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cadenzalabs.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# VLA mode & GRD

> Adapt a vision-language-action model with one governed fine-tune + RL loop — no env.json, no prompts.

VLA-only mode is the path for adapting a **vision-language-action model** without
the full Cadenza mission stack. A VLA project is just two things in a `vla.json`:
a **model** and an **action library**. The **GRD** loop then adapts *only* the
model's LoRA adapter — the VLA itself stays frozen — in a single governed pass
that mixes imitation and RL.

<Warning>
  The GRD loop needs the **`lora`** extra (`pip install -e ".[lora]"`). Loading a
  *real* downloaded model (`smolvla` / `hf` / `local`) additionally needs the
  **`vla`** extra (`pip install -e ".[vla]"`, which adds `transformers` + `lerobot`).
  The governed commands require [sign-in](/cli-setup/authentication).
</Warning>

## `env vla init`: scaffold a model + action library

```bash theme={null}
cadenza env vla init reach-arm --robot franka --model default
```

| Flag                                  | Default   | Purpose                                                                                          |
| ------------------------------------- | --------- | ------------------------------------------------------------------------------------------------ |
| `--robot <name>`                      | `go1`     | Robot whose action library to attach.                                                            |
| `--model default\|smolvla\|hf\|local` | `default` | Which backbone to adapt. `default` uses the built-in stable encoder; the others load a real VLA. |
| `--model-id <repo\|path>`             | —         | HF repo id (`hf`) or local path (`local`/`smolvla`).                                             |
| `--force`                             | off       | Overwrite an existing `vla.json`.                                                                |

Writes `reach-arm/vla.json`. Inspect it any time with `env vla show reach-arm`.

## `env vla data`: author goal→action pairs

GRD's imitation signal comes from goal→action examples you author against the
model's action library.

```bash theme={null}
# add one pair
cadenza env vla data reach-arm add "reach the red block" \
  --steps 'move_forward 1.0, lower_arm 0.5, close_gripper'

# list the whole dataset
cadenza env vla data reach-arm
```

## `env vla grd`: the governed GRD loop

GRD = **Govern · Refine · Decide**. In one loop it fine-tunes the LoRA adapter on
your goal→action data (imitation) and RL-tunes it, then asks the Cadenza API for a
verdict. The API **steers the loop** — it sets three dials and returns
`DEPLOY | BLOCK | NEEDS_DATA`:

| Dial               | What it controls                                                |
| ------------------ | --------------------------------------------------------------- |
| `--lambda <l>`     | The imitation ↔ RL mix.                                         |
| `--rl-budget <n>`  | How much RL the round is allowed.                               |
| `--change-cap <c>` | How far the adapter may move from the frozen base in one round. |

```bash theme={null}
cadenza env vla grd reach-arm --rounds 4
```

| Flag               | Default     | Purpose                                         |
| ------------------ | ----------- | ----------------------------------------------- |
| `--lambda <l>`     | API-steered | Imitation/RL mix (the API overrides per round). |
| `--rl-budget <n>`  | API-steered | RL budget per round.                            |
| `--change-cap <c>` | API-steered | Per-round adapter change cap.                   |
| `--rounds <r>`     | —           | Max GRD rounds before stopping.                 |
| `--device <d>`     | auto        | Training device.                                |

Only the LoRA adapter is trained; the VLA stays frozen throughout.

## `env vla eval`: one-shot governance

Score the current adapter without running a full loop:

```bash theme={null}
cadenza env vla eval reach-arm --promote
```

Returns the same `DEPLOY | BLOCK | NEEDS_DATA` verdict (see
[Governance](/cli/governance)); `--promote` deploys the adapter if it passes.

## Full loop

```bash theme={null}
cadenza env vla init reach-arm --robot franka --model default
cadenza env vla data reach-arm add "reach the red block" \
  --steps 'move_forward 1.0, lower_arm 0.5, close_gripper'
cadenza env vla grd reach-arm --rounds 4
cadenza env vla eval reach-arm --promote
```

<Note>
  VLA mode and the [LoRA action head](/cli/training-and-lora) both fine-tune a LoRA
  adapter, but they are different entry points: `env lora` adapts the action head
  **inside a full `env.json` mission**, while `env vla` adapts a standalone model
  with **no mission spec** — just a model and an action library.
</Note>