Sim-to-Real transfer for robotic locomotion using Recurrent PPO and Curriculum Learning. Designed to adapt to unmodeled physical variations in a custom MuJoCo Hopper environment.
-
Updated
Aug 14, 2026 - Python
#
sim2real
Here are 220 public repositories matching this topic...
This is a weekend project I’m doing for fun and to stay up-to-date with ROS 2. The Pickey-Car is basically a car with a 9-degree-of-freedom robot hand strapped to the top. I’m building everything for both simulation and real hardware environments.
-
Updated
Sep 1, 2025 - Python
[FAIML-26] Starting code for Reinforcement Learning project
-
Updated
Apr 8, 2026 - Python
GPU-accelerated RL training for SO-ARM100/101 robotic arms in NVIDIA Isaac Lab. Reach and Lift tasks via PPO. Exports to .pt and .onnx.
-
Updated
Apr 27, 2026 - Python
基于 Microduck 路线的拓展性复现：10DOF 双足硬件、MuJoCo 强化学习、Hardware-First Sim2Real 与安全 Agent。
python raspberry-pi reinforcement-learning robotics robot-learning mujoco ppo onnx hardware-in-the-loop sim2real biped-robot wsl2 embodied-ai sim-to-real physical-ai microduck mini-duck hardware-first
-
Updated
Sep 5, 2026 - Python
Source code for simulating inflatable particles in voxcraft
-
Updated
Jun 8, 2024
Fork of HansZ8/RoboJuDo adding ProtoMotions tracker deployment for the Unitree G1: reference-mode blending in the tracker policy, the unitree_cpp build patch, and a G1 deployment runbook. Check out integration/all.
-
Updated
Sep 3, 2026 - Python
Stable Planning through Aligned Representations in Model-Based Reinforcement Learning (RLC 2026)
-
Updated
Sep 23, 2026 - Python
SynReal: an Attention-Guided GAN architecture for Unpaired Image 2 Image Domain Translation.
-
Updated
Sep 12, 2025 - Jupyter Notebook
让普通 AI 开发者用 3000 元以内进入 Physical AI 的开放平台：国产硬件 + 仿真 + RL + Sim2Real + Robot HAL
reinforcement-learning robotics servo open-hardware open-source-hardware humanoid biped mujoco onnx sim2real embodied-ai lerobot physical-ai robot-hal
-
Updated
Sep 2, 2026
🚀 Explore a modular platform for reinforcement learning, featuring real-time visualization and state-of-the-art algorithms tailored for Lunar Lander experimentation.
python agent reinforcement-learning robotics simulation pytorch mdp reinforcement-learning-algorithms robotframework locomotion vla humanoid-robot humanoid reasoning quadruped go1 planning-algorithms sim2real sim-to-real unitree
-
Updated
Feb 3, 2026
Swimming eel robot with CPG + RL control
-
Updated
Dec 17, 2025 - Python
Manager for add-ons in the BenchBot software stack: https://github.com/qcr/benchbot
-
Updated
Mar 12, 2023 - Python
A drone that learns to efficiently find non-uniformly distributed objects in agricultural fields: from simulation to the real world
-
Updated
Aug 4, 2026 - Python
Fork of NVlabs/ProtoMotions adding Unitree G1 23-DoF support and sim2real tooling: robot config, MJCF/USD assets, qpos to .motion converter, domain randomization and MuJoCo sim2sim validation. Work lives on the feature branches; check out integration/all.
reinforcement-learning robotics motion-retargeting motion-tracking mujoco sim2real humanoid-robotics isaac-lab unitree-g1
-
Updated
Sep 3, 2026 - Python
MicroDuck × RDK-X5 robot learning workbench: simulate, record, train locally or on RoboGo, evaluate Sim2Real, and deploy safely.
-
Updated
Oct 5, 2026 - TypeScript
Sim-to-real RL for all 56 equilibrium transitions of a triple inverted pendulum on a cart. MuJoCo + TQC + n8n-orchestrated pipeline.
control reinforcement-learning robotics open-hardware pytorch gymnasium inverted-pendulum mujoco cart-pole sim2real mlflow n8n sim-to-real stable-baselines3 tqc
-
Updated
Jul 2, 2026 - Python
Interactive sandbox for building a deep intuition for MuJoCo's physics solver
-
Updated
Sep 28, 2026 - Python
Add this topic to your repo
To associate your repository with the sim2real topic, visit your repo's landing page and select "manage topics."