Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.
| Date | Stars |
|---|---|
| 2026-07-31 | 477 |
| 2026-08-01 | 477 |
| 2026-08-02 | 477 |
| 2026-08-06 | 477 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<img align="left" width="60" height="60" src="docs/media/robo-gym-logo.png" alt="robo-gym logo"> <!-- omit in toc --> # robo-gym <br>   **``robo-gym`` is an open source toolkit for distributed reinforcement learning on real and simulated robots.**   ``robo-gym`` provides a collection of reinforcement learning environments involving robotic tasks applicable in both simulation and real world robotics. Additionally, we provide the tools to facilitate the creation of new environments featuring different robots and sensors. Main features : - [Gymnasium](https://gymnasium.farama.org/) interface for all the environments - **simulated** and **real** robots interchangeability, which enables a seamless transfer from training in simulation to application on the real robot. - built-in **distributed** capabilities, which enable the use of distributed algorithms and distributed hardware - based only on **open source** software, which allows to develop applications on own hardware and without incurring in cloud services fees or software licensing costs - integration of multiple commercially available **industrial robots**: MiR 100, Universal Robots (more to come) - it has been successfully deployed to train a DRL algorithm to solve two different tasks in simulation that was able to solve the tasks on the real robots as well, without any further training in the real world A [paper](https://arxiv.org/abs/2007.02753) describing robo-gym has been accepted for IROS 2020. A video showcasing the toolkit's capabilities and additional info can be found on our [website](https://sites.google.com/view/robo-gym) **NOTE**: We are continuously working to improve and expand robo-gym. If you are interested in reproducing the results obtained in the IROS 2020 paper please refer to v.0.1.0 for all the 3 repositories involved in the framework: [robo-gym](https://github.com/jr-robotics/robo-gym/tree/v0.1.0), [robo-gym-robot-servers](https://github.com/jr-robotics/robo-gym-robot-servers/tree/v0.1.0), [robo-gym-server-modules](https://github.com/jr-robotics/robo-gym-server-modules/tree/v0.1.0). **NOTE**: robo-gym is undergoing a necessary overhaul process. Things may break temporarily, and some old setups may not be supported anymore. In particular: * Agents using the old Gym versions need to upgrade to Gymnasium, see also [Gymnasium's migration guide](https://gymnasium.farama.org/content/migration-guide/). * Across all components, Python versions up to 3.7.x will not be supported anymore. * On the server side, ROS distros before noetic will not be supported anymore. * Installation guides and other documentation may be inconsistent and not up to date. * Version-agnostic references to robo-gym repositories from old commits (e.g., git clone commands in Dockerfiles) may need adjustment to retrieve a compatible version. * Temporarily, our internal CI for robo-gym is partially disabled, which may lead to reduced coverage of automated tests and delays in updates on PyPI. Install from source instead (`pip install -e .`) if required. [See the News section](#news) <!-- omit in toc --> # Table of Contents - [Basics](#basics) - [Installation](#installation) - [How to use](#how-to-use) - [Environments](#environments) - [Examples](#examples) - [Testing](#testing) - [Troubleshooting](#troubleshooting) - [Contributing](#contributing) - [Citation](#citation) - [News](#news) # Basics [back to top](#robo-gym) The ``robo-gym`` framework is composed of several building blocks. Detailed information on them is given [here](docs/the_framework.md) and in the [paper](https://arxiv.org/abs/2007.02753). ![robo-gym framework](https://user-images.gith
Excerpt of 13,093 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d4deee1dd7ddf004, llm:Repository topics: openai-gym, reinforcement-learning-environments, robo-gym, robotics; description: 'An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.'
matched fp:d4deee1dd7ddf004, llm:Repository topics: openai-gym, reinforcement-learning-environments, robo-gym, robotics; description: 'An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.'
matched fp:d4deee1dd7ddf004, llm:Repository topics: openai-gym, reinforcement-learning-environments, robo-gym, robotics; description: 'An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.'