ROS2Learn: a reinforcement learning framework for ROS 2
This work addresses the challenge of applying reinforcement learning to modular robotics for researchers and practitioners, but it is incremental as it adapts existing algorithms to a new framework.
The authors tackled the problem of training modular robots using deep reinforcement learning by developing a framework that integrates with ROS 2 and Gazebo, achieving results through empirical evaluation in simulation across four environments.
We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics to train a robot directly from joint states, using traditional robotic tools. We use an state-of-the-art implementation of the Proximal Policy Optimization, Trust Region Policy Optimization and Actor-Critic Kronecker-Factored Trust Region algorithms to learn policies in four different Modular Articulated Robotic Arm (MARA) environments. We support this process using a framework that communicates with typical tools used in robotics, such as Gazebo and Robot Operating System 2 (ROS 2). We evaluate several algorithms in modular robots with an empirical study in simulation.