Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo

Iker Zamora, Nestor Gonzalez Lopez, Victor Mayoral Vilches, Alejandro Hernandez Cordero
8/19/2016
cs.RO
rl

Official code: erlerobot/gym-gazebo (844 stars, GPL-3.0, last commit 2019-03-16).

Abstract

This paper presents an extension of the OpenAI Gym for robotics using the Robot Operating System (ROS) and the Gazebo simulator. The content discusses the software architecture proposed and the results obtained by using two Reinforcement Learning techniques: Q-Learning and Sarsa. Ultimately, the output of this work presents a benchmarking system for robotics that allows different techniques and algorithms to be compared using the same virtual conditions.

View on arXivView PDF

Code Implementations(1)

erlerobot/gym-gazeboOfficial100%
GPL-3.0

Refer to https://github.com/AcutronicRobotics/gym-gazebo2 for the new version

844275Shell, PythonAug 19, 20167 years agoGPL-3.0
deep-reinforcement-learningdrlgazeboopenai-gymreinforcement-learning+3 more

Similar Papers

Benchmarking Reinforcement Learning Algorithms on Real-World Robots

86% match1 repo2212018

A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges

85% match2023

MARBLER: An Open Platform for Standardized Evaluation of Multi-Robot Reinforcement Learning Algorithms

84% match1 repo142023

Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments

84% match2 repos8.4k2023

An Architecture for Unattended Containerized (Deep) Reinforcement Learning with Webots

83% match2024

Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World

83% match2023

Cite this paper

@article{zamora2016extending,
  title  = {Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo},
  author = {Iker Zamora and Nestor Gonzalez Lopez and Victor Mayoral Vilches and Alejandro Hernandez Cordero},
  year   = {2016},
  eprint = {1608.05742},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1608.05742}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1608.05742.svg)](https://codeofpaper.com/paper/1608.05742)

Discussion