# \[RLlib\] Wrapper for Gazebo?

**URL:** <https://discuss.ray.io/t/rllib-wrapper-for-gazebo/2389>\
**Category:** RLlib\
**Created:** [June 2, 2021, 8:00pm UTC](https://discuss.ray.io/t/rllib-wrapper-for-gazebo/2389 "2021-06-02T20:00:58Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Hihihoho](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/hihihoho/32/1073_2.png) [@Hihihoho](https://discuss.ray.io/u/Hihihoho)\
**Post date:** [June 2, 2021, 8:00pm UTC](https://discuss.ray.io/t/rllib-wrapper-for-gazebo/2389/1 "2021-06-02T20:00:58Z")

</div>

Hello, I am trying to utilize RLlib to do reinforcement learning for my simulation running in Gazebo. Do we have a wrapper for gazebo?

If I want to set up my own gazebo wrapper, should the wrapper be similar to the unity3D\_env.py where we define functions like step(), reset(), \_get\_step\_result()?

---

<div class="post-metadata">

**Author:** ![michaelzhiluo](https://avatars.discourse-cdn.com/v4/letter/m/41988e/32.png) [@michaelzhiluo](https://discuss.ray.io/u/michaelzhiluo)\
**Post date:** [June 3, 2021, 2:37am UTC](https://discuss.ray.io/t/rllib-wrapper-for-gazebo/2389/2 "2021-06-03T02:37:50Z")

</div>

Try this one out: [GitHub - AcutronicRobotics/gym-gazebo2: gym-gazebo2 is a toolkit for developing and comparing reinforcement learning algorithms using ROS 2 and Gazebo](https://github.com/AcutronicRobotics/gym-gazebo2)