[ros-users] [Discourse.ros.org] [General] A toolkit for Reinforcement Learning using ROS and Gazebo
Víctor Mayoral Vilches
ros.discourse at gmail.com
Fri Sep 7 17:54:03 UTC 2018
For those interested, a follow up work on this topic that will be presented at ROSCon this year:
**Accelerated robot training through simulation in the cloud with ROS and Gazebo**
_Rather than programming, training allows robots to achieve behaviors that generalize better and are capable to respond to real-world needs. However, such training requires a big amount of experimentation which is not always feasible for a physical robot. In this work, we present robot_gym, a framework to accelerate robot training through simulation in the cloud that makes use of roboticists tools, simplifying the development and deployment processes on real robots. We unveil that, for simple tasks, simple 3DoF robots require more than 140 attempts to learn. For more complex, 6DoF robots, the number of attempts increases to more than 900 for the same task. We demonstrate that our framework, for simple tasks, accelerates the robot training time by more than 33% while maintaining similar levels of accuracy and repeatability._
Full article available at https://arxiv.org/pdf/1808.10369.pdf.
[Visit Topic](https://discourse.ros.org/t/a-toolkit-for-reinforcement-learning-using-ros-and-gazebo/442/17) or reply to this email to respond.
More information about the ros-users