Skip to content
Source notesOfficial source

MicroDuck RL Repository: Training Workflow & Export

The official MicroDuck RL repository is the source for training setup, cloud jobs and policy workflows. Start with its current quick start, then record the revision and compute environment used for an experiment. Our site provides preparation notes and does not run training jobs.

THE MICRODUCK PLATFORMOfficial photo
A MicroDuck robot beside a laptop with code on screen.A seated MicroDuck robot on a desk in front of a computer.
Photo: Pollen Robotics ↗

Separate the activities.

The official repository documents training and policy workflows. Its quick start requires a CUDA GPU, and it also includes a cloud jobs route.

From source to useful preparation.

Use the repository’s current requirements and record the revision for an experiment. Our readiness check helps organize those questions; it does not run a training job.

SOURCES & REVIEW

Source check: . Verification scope is stated in the guide; source review alone is not a hardware test.

Where to go next.

CONTINUE THE CONVERSATION

What would you like to understand next?

Keep the source, your environment and your observations together.

Before you continue

Does a public training repository prove reproducibility?

No. Reproduction also needs matching dependencies, task configuration, checkpoints and teacher files. Follow the practical training and export guides.

Applies to: Pollen Robotics MicroDuck. Keep the model, image, software and driver versions together. The dated sections below retain their original verification limits.

Source checked:

Sources and review (1)
  1. github.com/pollen-robotics/microduck_rl

Next useful guides

MicroDuck training to deployment: a complete reading path

Follow preparation, local training, export, simulation replay and deployment checks in order. A successful export or upload is not evidence that the robot can execute the policy.

MicroDuck Local Training: Setup, Checks & First Run

Prepare the official MicroDuck RL environment with a pinned revision, Python 3.12, a CUDA check and a short training run before a longer experiment.

MicroDuck ONNX Export: Checkpoints, Replay & Validation

Export a MicroDuck checkpoint with observation normalization, select the correct playback input layout and inspect a policy package before sharing.