Skip to main content
Building a robot that learns is a layered problem. A working physical-AI system is not one model — it’s a stack, where each layer depends on the ones beneath it. Understanding those layers makes it clear where the hard parts are and how the pieces fit together. This page is a general map of that stack. The rest of the Concepts section zooms into the layers that matter most for learning robots.

The layers

Models

The learned components — vision-language-action (VLA) models, world models, and perception. They turn raw sensory input and intent into a plan.

Policies

The decision layer: a function from observation to action. A policy is what you actually train and deploy.

Control & actions

The vocabulary of motion — gaits, grasps, balance, recovery — composed into the behaviors a policy can call on.

Simulation & physics

The environment the robot acts in. High-fidelity physics is where policies are trained and validated before touching hardware.

Data & training

Rollouts, rewards, and the pipelines that turn experience into better policies through RL and fine-tuning.

Software infrastructure

The connective tissue — orchestration, logging, evaluation, and deployment drivers that make the whole loop reproducible.

Models vs the rest of the stack

It’s tempting to think physical AI is “just” a model problem. It isn’t. A state-of-the-art model is useless without:
  • a simulator good enough to train and test it safely,
  • a control layer that turns its outputs into stable motion,
  • a data pipeline that captures and labels what happened,
  • and infrastructure to run, evaluate, and deploy it.
Most of the engineering effort — and most of the time lost — lives in the layers around the model. That’s exactly the gap Cadenza is built to close.

How Cadenza maps onto the stack

LayerIn Cadenza
ModelsBring your own VLA / world model, or use the built-in inference stack
PoliciesTrained and fine-tuned with RL + LoRA
Control & actionsThe reusable, phase-aware action library
Simulation & physicsThe MuJoCo-based simulator with Go1 / G1 robots
Data & trainingAutomatic rollout logging, scoring, and fine-tuning
Software infrastructureThe SDK foundation + the CLI workflow, plus deploy drivers

Next: Models & policies

Zoom into the model layer — VLA models, world models, and what a policy is.