> ## 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.

# Models & policies

> The model layer of physical AI — VLA models, world models, and what a policy actually is.

At the top of the [stack](/labs/the-stack) sit the learned components. This page
explains the kinds of models that drive a robot and how they relate to the
**policy** — the thing you ultimately train and deploy.

## What is a policy?

A **policy** is a function from what the robot senses to what it does:

```
observation  ->  policy  ->  action
```

Everything else in physical AI exists to produce, train, or run a good policy. A
policy can be a small neural network, a large multimodal model, or a composition
of several models working together.

* **Observation** — the robot's view of the world this tick: joint states, camera
  frames, proprioception, sometimes a language instruction.
* **Action** — the command the policy emits: target velocities, joint torques, or
  a higher-level action call.

## Vision-language-action (VLA) models

A **VLA model** is a policy that takes in **pixels and language** and outputs
**actions**. It's the robotics analogue of a multimodal LLM: instead of replying
with text, it replies with motion.

VLA models are powerful because they:

* generalize across tasks described in natural language ("pick up the red block"),
* fuse perception and intent in a single model,
* and start from broad pretraining, so you can **specialize** them with relatively
  little task-specific data.

That last point is why [fine-tuning](/labs/fine-tuning) matters so much: you rarely
train a VLA from scratch — you adapt a capable base model to your robot and task.

## World models

A **world model** learns to *predict* — given the current state and a candidate
action, what happens next. Instead of mapping observation straight to action, a
world model lets a system **imagine** outcomes and plan against them.

World models are useful for:

* **Planning** — search over imagined rollouts before committing to an action.
* **Sample efficiency** — learn from predicted experience, not just real or
  simulated steps.
* **Reasoning** — chain predictions together for multi-step tasks.

## How they fit together

These aren't mutually exclusive. A real system often layers them:

```mermaid theme={null}
flowchart LR
    OBS["Observation<br/>pixels + language"] --> VLA["VLA model"]
    OBS --> WM["World model"]
    WM -->|predicted outcomes| PLAN["Planner"]
    VLA -->|proposed action| ACT["Action"]
    PLAN -->|chosen action| ACT
```

In Cadenza, the [inference stack](/sdk/inference-stack) is built to host exactly
this: register your own VLA or world model, or compose them — sequential,
chain-of-thought, or custom — behind one clean interface. The simulator provides
the observations; your model provides the actions.

<CardGroup cols={2}>
  <Card title="How policies learn: RL" icon="arrow-right" href="/labs/reinforcement-learning">
    Trial, error, and reward.
  </Card>

  <Card title="Specializing a model: fine-tuning" icon="arrow-right" href="/labs/fine-tuning">
    Adapt a base model to your robot with LoRA.
  </Card>
</CardGroup>