ROS2Learn: a reinforcement learning framework for ROS 2
arXiv:1903.06282
Abstract
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.
References in corpus (6)
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
- Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
- Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo
- 3D Simulation for Robot Arm Control with Deep Q-Learning
- gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo
- Deep Predictive Policy Training using Reinforcement Learning