"a reinforcement learning framework for ROS 2"
ROS 2 enabled Artificial Intelligence (AI) and Reinforcement Learning (RL) algorithms that run in selected environments.
In the gif above, a trained MARA robot using PPO2-MLP achieves the given target with high accuracy. You will find the code to replicate this learning in the ROS2Learn github repository.
Take a look at the tutorials section for detailed explanations of various key concepts and multiple usage video-tutorials. You might also find useful the gym-gazebo2 tutorials section.
Read more about this topic in our related publications: