This post was written by Miguel A. Rodriguez and Ricardo Tellez   In this post we are going to see how to test different reinforcement learning (RL) algorithms from the OpenAI framework in the same robot trying to solve the same task. We are going to use the openai_ros package, which allows to change algorithms

  This is an extra short video updating what it has been done new on OpenAI_ROS package. You can find the link to the package wiki down below. This is important for the people that saw the other two videos, because the structure of the package has changed and it might lead to some confusion

  What you will learn? In this video you will learn how to use openai_ros package to make learn the WAM-V sea robot of the RobotX Challenge to pass the first Navigation Control.  The only thing you need to code is the AI algorithm if you want to use a different one to the one

  In this second part, you will continue by creating your own TaskEnvironment for a different TurtleBot simulation environment with a wall. You will create this Task Env that allows the robot to learn how to reach a certain position in the map without running into the wall. Related links and resources: Here is the

  In this new video series, we are going to learn how to use the openai_ros package created by TheConstruct. You will learn to use it with all the robots that we give suport to. You will learn in this video divided into two parts, how to use openai_ros with Turtlebot2. You will learn how