Gym-Ignition: Reproducible Robotic Simulations for Reinforcement Learning

Abstract

This paper presents Gym-Ignition, a new framework to create reproducible robotic environments for reinforcement learning research. It interfaces with the new generation of Gazebo, part of the Ignition Robotics suite, which provides three main improvements for reinforcement learning applications compared to the alternatives: 1) the modular architecture enables using the simulator as a C++ library, simplifying the interconnection with external software; 2) multiple physics and rendering engines are supported as plugins, simplifying their selection during the execution; 3) the new distributed simulation capability allows simulating complex scenarios while sharing the load on multiple workers and machines. The core of Gym-Ignition is a component that contains the Ignition Gazebo simulator and exposes a simple interface for its configuration and execution. We provide a Python package that allows developers to create robotic environments simulated in Ignition Gazebo. Environments expose the common OpenAI Gym interface, making them compatible out-of-the-box with third-party frameworks containing reinforcement learning algorithms. Simulations can be executed in both headless and GUI mode, the physics engine can run in accelerated mode, and instances can be parallelized. Furthermore, the Gym-Ignition software architecture provides abstraction of the Robot and the Task, making environments agnostic on the specific runtime. This abstraction allows their execution also in a real-time setting on actual robotic platforms, even if driven by different middlewares.

arXiv commentAccepted in SII2020

References in corpus (15)

• Learning agile and dynamic motor skills for legged robots
• The Arcade Learning Environment: An Evaluation Platform for General Agents
• Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
• OpenAI Gym
• Unity: A General Platform for Intelligent Agents
• DeepMind Control Suite
• Challenges of Real-World Reinforcement Learning
• Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
• Assessing Transferability from Simulation to Reality for Reinforcement Learning
• Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie
• Gibson Env: Real-World Perception for Embodied Agents
• DeepMind Lab
• gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo
• Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer
• Hierarchical Reinforcement Learning for Quadruped Locomotion

Cited by in corpus (3)

• Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning
• On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning
• A RoboStack Tutorial: Using the Robot Operating System Alongside the Conda and Jupyter Data Science Ecosystems