Dear ROS community,
I am pleased to announce our next release of robo-gym : an open source toolkit for distributed reinforcement learning on real and simulated robots.
The toolkit is based on ROS and Gazebo.
If you don’t know about the project here is the post announcing robo-gym.
In this release:
- Added Obstacle Avoidance environments
- Added support for all the Universal Robots models: UR3, UR3e, UR5, UR5e, UR10, UR10e, UR16e
- Added support for ROS Noetic
- The Robot Server state can now be defined as a dictionary instead of a list to reduce errors caused by wrong indexing
- Added support for Python 3.7, 3.8, 3.9 and stopped support for 3.5
- Improved logging and debugging
- Improved code quality and readability
How to contact us
If you encounter any issues with robo-gym the best way to contact us is to directly open a new issue on GitHub.
If you are interested in expanding the framework or start a collaboration please drop us an email at