https://github.com/ashwinreddy/rlg

Robot Learning Gym
https://github.com/ashwinreddy/rlg

deep-learning robot-learning robotics

Last synced: 6 months ago
JSON representation

Robot Learning Gym

• Host: GitHub
• URL: https://github.com/ashwinreddy/rlg
• Owner: ashwinreddy
• License: mit
• Created: 2016-12-22T22:41:11.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2017-02-24T22:53:07.000Z (over 9 years ago)
• Last Synced: 2025-09-08T13:23:00.280Z (10 months ago)
• Topics: deep-learning, robot-learning, robotics
• Language: Python
• Size: 27.9 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# RLG: Robot Learning Gym

Robot Learning Gym is a tool to test reinforcement learning algorithms for robotics tasks a la OpenAI's [Universe](https://universe.openai.com/) and/or [Gym](https://gym.openai.com).

The purpose is to evaluate how well various RL algorithms work on robotics (motor/manipulation) tasks by using standardized and consistent metrics.

To do this, RLG supports the ability to easily add robots and tasks in order to evaluate performance on a large repertoire of tasks. This makes it possible to quickly and easily test which conditions algorithms work best and worse under.

To learn more, visit the [wiki](https://github.com/ashwinreddy/rlg/wiki).

**CAUTION: RLG is still in development, documentation may be incorrect, and code may be buggy**

---

Dependencies:

- MuJoCo

- TensorFlow 1.0 (previous versions won't work)

- OpenAI Gym

- Others (will update soon)