Downloads · 30 days
0
microduck-models
minjunglee27/microduck-models
microduck-models is a reinforcement learning model from minjunglee27. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This repository contains trained Reinforcement Learning (RL) policies and checkpoints for the MicroDuck bipedal robot simulation and Sim2Real transfer.
Access
Public
Updated Sep 4, 2026
Repo size
18.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt9.7 MB · 53%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026
- SHA
- d78e5b1c
Model card
From the Hugging Face model README
MicroDuck Robot RL Models & Policies
This repository contains trained Reinforcement Learning (RL) policies and checkpoints for the MicroDuck bipedal robot simulation and Sim2Real transfer.
📂 Contents
-
****: Pretrained ONNX policy networks ready for inference in MuJoCo / robot deployment:
- ****:
- : Exported policy checkpoint at 750 iterations.
- ****:
- Raw PyTorch checkpoints (, ).
🛠️ Usage
Download with huggingface_hub:
from huggingface_hub import hf_hub_download
model_path = hf_hub_download(repo_id="minjunglee27/microduck-models", filename="policies/alpha_walking.onnx")
- Task
- Reinforcement Learning
- Created
- Sep 4, 2026
- Updated
- Sep 4, 2026