Jump playground

Browser sandbox fork with a custom-trained vertical-jump policy; live demo. Sim-only.

Project Overview

Fork of the pollen-robotics/microduck-simulator Hugging Face Space, extended with a custom-trained vertical jump policy (PPO, trained with apirrone/mjlab microduck on the Mjlab-Jump-Flat-MicroDuck task added in this fork — see training/ ). All credit for the original simulator, robot, models and policies goes to Pollen Robotics and @apirrone. Live at duck.liyucheng.me.

Real trained RL policies for the Microduck robot, running fully in the browser: MuJoCo compiled to WebAssembly steps the physics, onnxruntime-web runs the policy network at 50 Hz. No server, no backend.

Two locomotion variants of the same robot are included: legs (walking, the default) and rollers (the wheeled skating variant). Press M (or hold D-pad up ~1 s on a gamepad) to switch; the roller model, meshes and policies are lazy-loaded on the first switch.

Task

Field	Value
Source	GITHUB SOURCE
Runtime contract	61 observations / 14 actions / 50 Hz
Verification	Pending independent Duckio review
Artifact	Not indexed

Source Coverage

The upstream README includes: Policies, Controls, URL parameters, Gamepad, Multiplayer ghosts, How it works, Development.

Intended Use

Use this entry to assess the project and locate its canonical implementation. Read the complete README, inspect the manifest and artifacts, and reproduce the source's evaluation before assigning simulation or hardware verification.