Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

fan-ziqi/rl_sar

Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

67Apache-2.0C++

View on GitHub

Stars: 1,419
Forks: 187
Watchers: 1,419
Open issues: 18
Contributors: 8

Star history, last 90 days+9 over 6 snapshots

2026-07-31 · 1,4102026-08-06 · 1,419

Star history, last 90 days
Date	Stars
2026-07-31	1410
2026-08-02	1411
2026-08-03	1411
2026-08-04	1414
2026-08-05	1417
2026-08-06	1419

Today

+2 stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

# rl_sar

[![Ubuntu 20.04/22.04](https://img.shields.io/badge/Ubuntu-20.04/22.04-blue.svg?logo=ubuntu)](https://ubuntu.com/)
[![macOS](https://img.shields.io/badge/macOS-Experimental-orange.svg?logo=apple)](https://www.apple.com/macos/)
[![ROS Noetic](https://img.shields.io/badge/ros-noetic-brightgreen.svg?logo=ros)](https://wiki.ros.org/noetic)
[![ROS2 Foxy/Humble](https://img.shields.io/badge/ros2-foxy/humble-brightgreen.svg?logo=ros)](https://wiki.ros.org/foxy)
[![Gazebo](https://img.shields.io/badge/Gazebo-Classic-lightgrey.svg?logo=gazebo)](http://gazebosim.org/)
[![MuJoCo](https://img.shields.io/badge/MuJoCo-3.2.7-orange.svg?logo=mujoco)](https://mujoco.org/)
[![License](https://img.shields.io/badge/license-Apache2.0-yellow.svg?logo=apache)](https://opensource.org/license/apache-2-0)

[中文文档](README_CN.md)

This repository provides a framework for simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" stands for "simulation and real"

> Supports both **IsaacGym** and **IsaacSim**
>
> Supports both **ROS-Noetic** and **ROS2-Foxy/Humble**
>
> Supports both **libtorch** and **onnxruntime**
>
> Supports both **Linux** and **macOS**(Only support Mujoco simulation)
>
> Supports both **Gazebo** and **Mujoco**(Partial support)
>
> Supports both **Locomotion** and **Dance**

Support List:

|Robot Name (rname:=)|Pre-Trained Policy|Gazebo|Mujoco|Real|
|-|-|-|-|-|
|Unitree-A1 (a1)|legged_gym (IsaacGym)|✅|❌|✅|
|Unitree-Go2 (go2)|himloco (IsaacGym)</br>robot_lab (IsaacSim)|✅|✅|✅</br>✅|
|Unitree-Go2W (go2w)|robot_lab (IsaacSim)|✅|✅|✅|
|Unitree-B2 (b2)|robot_lab (IsaacSim)|✅|✅|⚪|
|Unitree-B2W (b2w)|robot_lab (IsaacSim)|✅|✅|⚪|
|Unitree-G1 (g1)|robomimic/locomotion (IsaacGym)</br>robomimic/charleston (IsaacGym)</br>whole_body_tracking/dance_102 (IsaacSim)</br>whole_body_tracking/gangnam_style (IsaacSim)|✅|✅|✅|
|FFTAI-GR1T1 (gr1t1)</br>(Only available on Ubuntu20.04)|legged_gym (IsaacGym)|✅|❌|⚪|
|FFTAI-GR1T2 (gr1t2)</br>(Only available on Ubuntu20.04)|legged_gym (IsaacGym)|✅|❌|⚪|
|zhinao-L4W4 (l4w4)|legged_gym (IsaacGym)|✅|❌|✅|
|Deeprobotics-Lite3 (lite3)|himloco (IsaacGym)|✅|❌|✅|
|Agibot-D1 (d1)|robot_lab (IsaacSim)|✅|✅|✅|
|DDTRobot-Tita (tita)|robot_lab (IsaacSim)|✅|❌|⚪|

> [!IMPORTANT]
> Python version temporarily suspended maintenance, please use [v2.3](https://github.com/fan-ziqi/rl_sar/releases/tag/v2.3) if necessary, may be re-released in the future.

> [!NOTE]
> If you want to train policy using IsaacLab(IsaacSim), please use [robot_lab](https://github.com/fan-ziqi/robot_lab) project.
>
> The order of joints in robot_lab cfg file `joint_names` is the same as that defined in `xxx/robot_lab/config.yaml` in this project.
>
> Discuss in [Github Discussion](https://github.com/fan-ziqi/rl_sar/discussions) or [Discord](http://www.robotsfan.com/dc_rl_sar).

> [!CAUTION]
> **Disclaimer: User acknowledges that all risks and consequences arising from using this code shall be solely borne by the user, the author assumes no liability for any direct or indirect damages, and proper safety measures must be implemented prior to operation.**

## Preparation

Clone the repository

```bash
git clone --recursive --depth 1 https://github.com/fan-ziqi/rl_sar.git
```

To update

```bash
git pull
git submodule update --init --recursive --recommend-shallow --progress
```

## Dependency

Install the required packages:

```bash
# Ubuntu
sudo apt install cmake g++ build-essential libyaml-cpp-dev libeigen3-dev libboost-all-dev libspdlog-dev libfmt-dev libtbb-dev liblcm-dev

# macOS
brew install boost lcm yaml-cpp tbb libomp pkg-config glfw
```

If you need to use ROS, install the following dependency packages:

```bash
# ros-noetic (Ubuntu20.04)
sudo apt install ros-noetic-teleop-twist-keyboard ros-noetic-controller-interface ros-noetic-gazebo-ros-control ros-noetic-joint-state-controller ros-noetic-effort-controllers ros-noetic-joint-trajectory-control

Excerpt of 21,158 characters

Read on GitHub

Top contributors8 shown

fan-ziqi
Ziqi Fan · ZSTU & NJUST · China
235
XuaaanQWQ
3
cmjang
1
MiaoDX
MiaoDX · XiaomiEV
1
SenSen77
1
1170632760
1
zma69650
1
lovelyyoshino
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

67/10067

Maintenance: 70%; How recently the default branch was pushed to
Releases: 54%; Recency and cadence of tagged releases
Community: 24%; Contributor breadth and bus factor
Issue backlog: 85%; Open issues measured against the size of the audience
Documentation: 93%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

Bus factor of 1 — one contributor dominates
Usable in commercial products with attribution.

Details

Created: 2 years ago
Last push: 2 months ago
Last release: 5 months ago
Release tag: v4.1.0
Releases in the last year: 3
Default branch: main
Size: 222k KB
Owner type: User
Owner location: Nanjing
Discovered via: phrase:reinforcement learning
First indexed: 7 days ago
Last synced: 4 days ago

fan-ziqi/rl_sar

Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

67Apache-2.0C++

View on GitHub

Stars: 1,419
Forks: 187
Watchers: 1,419
Open issues: 18
Contributors: 8

Star history, last 90 days+9 over 6 snapshots

2026-07-31 · 1,4102026-08-06 · 1,419

Star history, last 90 days
Date	Stars
2026-07-31	1410
2026-08-02	1411
2026-08-03	1411
2026-08-04	1414
2026-08-05	1417
2026-08-06	1419

Today

+2 stars today

This week

— stars this week

This month

— stars this month

Momentum

0.0

growth rate 0.00%/day

From the README

# rl_sar

[![Ubuntu 20.04/22.04](https://img.shields.io/badge/Ubuntu-20.04/22.04-blue.svg?logo=ubuntu)](https://ubuntu.com/)
[![macOS](https://img.shields.io/badge/macOS-Experimental-orange.svg?logo=apple)](https://www.apple.com/macos/)
[![ROS Noetic](https://img.shields.io/badge/ros-noetic-brightgreen.svg?logo=ros)](https://wiki.ros.org/noetic)
[![ROS2 Foxy/Humble](https://img.shields.io/badge/ros2-foxy/humble-brightgreen.svg?logo=ros)](https://wiki.ros.org/foxy)
[![Gazebo](https://img.shields.io/badge/Gazebo-Classic-lightgrey.svg?logo=gazebo)](http://gazebosim.org/)
[![MuJoCo](https://img.shields.io/badge/MuJoCo-3.2.7-orange.svg?logo=mujoco)](https://mujoco.org/)
[![License](https://img.shields.io/badge/license-Apache2.0-yellow.svg?logo=apache)](https://opensource.org/license/apache-2-0)

[中文文档](README_CN.md)

This repository provides a framework for simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" stands for "simulation and real"

> Supports both **IsaacGym** and **IsaacSim**
>
> Supports both **ROS-Noetic** and **ROS2-Foxy/Humble**
>
> Supports both **libtorch** and **onnxruntime**
>
> Supports both **Linux** and **macOS**(Only support Mujoco simulation)
>
> Supports both **Gazebo** and **Mujoco**(Partial support)
>
> Supports both **Locomotion** and **Dance**

Support List:

|Robot Name (rname:=)|Pre-Trained Policy|Gazebo|Mujoco|Real|
|-|-|-|-|-|
|Unitree-A1 (a1)|legged_gym (IsaacGym)|✅|❌|✅|
|Unitree-Go2 (go2)|himloco (IsaacGym)</br>robot_lab (IsaacSim)|✅|✅|✅</br>✅|
|Unitree-Go2W (go2w)|robot_lab (IsaacSim)|✅|✅|✅|
|Unitree-B2 (b2)|robot_lab (IsaacSim)|✅|✅|⚪|
|Unitree-B2W (b2w)|robot_lab (IsaacSim)|✅|✅|⚪|
|Unitree-G1 (g1)|robomimic/locomotion (IsaacGym)</br>robomimic/charleston (IsaacGym)</br>whole_body_tracking/dance_102 (IsaacSim)</br>whole_body_tracking/gangnam_style (IsaacSim)|✅|✅|✅|
|FFTAI-GR1T1 (gr1t1)</br>(Only available on Ubuntu20.04)|legged_gym (IsaacGym)|✅|❌|⚪|
|FFTAI-GR1T2 (gr1t2)</br>(Only available on Ubuntu20.04)|legged_gym (IsaacGym)|✅|❌|⚪|
|zhinao-L4W4 (l4w4)|legged_gym (IsaacGym)|✅|❌|✅|
|Deeprobotics-Lite3 (lite3)|himloco (IsaacGym)|✅|❌|✅|
|Agibot-D1 (d1)|robot_lab (IsaacSim)|✅|✅|✅|
|DDTRobot-Tita (tita)|robot_lab (IsaacSim)|✅|❌|⚪|

> [!IMPORTANT]
> Python version temporarily suspended maintenance, please use [v2.3](https://github.com/fan-ziqi/rl_sar/releases/tag/v2.3) if necessary, may be re-released in the future.

> [!NOTE]
> If you want to train policy using IsaacLab(IsaacSim), please use [robot_lab](https://github.com/fan-ziqi/robot_lab) project.
>
> The order of joints in robot_lab cfg file `joint_names` is the same as that defined in `xxx/robot_lab/config.yaml` in this project.
>
> Discuss in [Github Discussion](https://github.com/fan-ziqi/rl_sar/discussions) or [Discord](http://www.robotsfan.com/dc_rl_sar).

> [!CAUTION]
> **Disclaimer: User acknowledges that all risks and consequences arising from using this code shall be solely borne by the user, the author assumes no liability for any direct or indirect damages, and proper safety measures must be implemented prior to operation.**

## Preparation

Clone the repository

```bash
git clone --recursive --depth 1 https://github.com/fan-ziqi/rl_sar.git
```

To update

```bash
git pull
git submodule update --init --recursive --recommend-shallow --progress
```

## Dependency

Install the required packages:

```bash
# Ubuntu
sudo apt install cmake g++ build-essential libyaml-cpp-dev libeigen3-dev libboost-all-dev libspdlog-dev libfmt-dev libtbb-dev liblcm-dev

# macOS
brew install boost lcm yaml-cpp tbb libomp pkg-config glfw
```

If you need to use ROS, install the following dependency packages:

```bash
# ros-noetic (Ubuntu20.04)
sudo apt install ros-noetic-teleop-twist-keyboard ros-noetic-controller-interface ros-noetic-gazebo-ros-control ros-noetic-joint-state-controller ros-noetic-effort-controllers ros-noetic-joint-trajectory-control

Excerpt of 21,158 characters

Read on GitHub

Top contributors8 shown

fan-ziqi
Ziqi Fan · ZSTU & NJUST · China
235
XuaaanQWQ
3
cmjang
1
MiaoDX
MiaoDX · XiaomiEV
1
SenSen77
1
1170632760
1
zma69650
1
lovelyyoshino
1

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

67/10067

Maintenance: 70%; How recently the default branch was pushed to
Releases: 54%; Recency and cadence of tagged releases
Community: 24%; Contributor breadth and bus factor
Issue backlog: 85%; Open issues measured against the size of the audience
Documentation: 93%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

Bus factor of 1 — one contributor dominates
Usable in commercial products with attribution.

Details

Created: 2 years ago
Last push: 2 months ago
Last release: 5 months ago
Release tag: v4.1.0
Releases in the last year: 3
Default branch: main
Size: 222k KB
Owner type: User
Owner location: Nanjing
Discovered via: phrase:reinforcement learning
First indexed: 7 days ago
Last synced: 4 days ago

Top AI Repos — open-source AI, indexed and scored

fan-ziqi/rl_sar

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details

fan-ziqi/rl_sar

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors8 shown

Quality score

What to know before adopting

Categories

Details