A comprehensive framework for reinforcement learning in robotics, which allows users to train their robots in both simulated and real-world environments.
MultiROS is an open-source ROS based simulation environment designed for concurrent deep reinforcement learning. It provides a flexible and scalable framework for training and evaluating reinforcement learning agents for complex robotic tasks.
This package provides ROS support for Stable Baselines3. It allows you to train robotics RL agents in the real world and simulations using ROS and SB3.
Explore the capabilities of RealROS and MultiROS in training robots for real-world tasks. This repository showcases real-world training and Gazebo simulation-based training for a reach task based on the ReactorX 200 robot manipulator.
Add a description, image, and links to the multiros topic page so that developers can more easily learn about it.
To associate your repository with the multiros topic, visit your repo's landing page and select "manage topics."