ROS2Learn, Deep Reinforcement Learning framework, provides an approach which trains a robot directly from joint states, with traditional robotic tools.
“We use a 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 environments around MARA modular robotic arm.” explains Risto Kojcev, Head of AI.
In a paper made available today, the team of researchers describe baseline implementations for the most common Deep Reinforcement Learning (DRL) techniques for policy iteration methods. And using this framework they present the results obtained benchmarking Deep Reinforcement Learning methods in a modular robotic arm with 6 degrees-of-freedom (DoF).
Using a Deep Reinforcement Learning framework that communicates with typical tools used in robotics, such as Gazebo and ROS 2 allows a more realistic representation of the environment. Moreover, they also compare the robustness of the performance of such methods in modular robots with an empirical study in robot simulation.
The results show that the proposed framework is stable during training of neural networks trough Deep Reinforcement Learning with policy-based methods.