API Reference

Detailed reference for the unilab Python package. Every public class, function, and submodule is auto-extracted from the source tree via sphinx.ext.autodoc + autosummary. If a symbol you expect is missing, please open an issue.

Note

Reading this in a preview build that says “no API reference”? The build environment couldn’t import unilab. Install UniLab in the same venv, or read this section on the live site.

Core foundations

🧱 unilab.base

The contracts everything else depends on: NpEnv, SimBackend, Registry, Scene.

unilab.base — Core Contracts
🧪 unilab.envs

Concrete tasks — locomotion, manipulation, motion tracking — layered on top of base.

unilab.envs — Tasks

Learning stack

🎛 unilab.algos

PPO / APPO / SAC / TD3 variants, in PyTorch and MLX flavours.

unilab.algos — Learning Algorithms
🏋 unilab.training

Runtime helpers, monitoring, reward bookkeeping, runner orchestration.

unilab.training — Training Runtime
🔗 unilab.ipc

Shared-memory rollout and replay primitives that connect CPU workers and the GPU learner.

unilab.ipc — Shared-Memory Runtime
🧮 unilab.backend

MuJoCo and Motrix adapters that implement SimBackend.

unilab.base.backend — Simulation Backends

Subsystems

🎲 unilab.dr

Declarative domain randomization manager.

unilab.dr — Domain Randomization
🏞 unilab.terrains

Procedural and heightfield terrain generators.

unilab.terrains — Procedural Terrain
👁 unilab.visualization

Scene rendering and viser bridges.

unilab.visualization — Visualization
🔧 unilab.tools

Scene export, NaN visualizer, ONNX export.

unilab.tools — CLI Tools
🧰 unilab.utils

Math, IO, and numerical helpers.

unilab.utils — Utilities
📝 unilab.logging

W&B / TensorBoard bridges and structured logging.

unilab.logging — Logging Adapters

Top-level package