https://github.com/aravindr93/mjrl

Reinforcement learning algorithms for MuJoCo tasks
https://github.com/aravindr93/mjrl

mujoco reinforcement-learning robotics simulation

Last synced: 5 days ago
JSON representation

Reinforcement learning algorithms for MuJoCo tasks

• Host: GitHub
• URL: https://github.com/aravindr93/mjrl
• Owner: aravindr93
• License: apache-2.0
• Created: 2018-04-12T17:07:05.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2024-06-10T18:44:13.000Z (6 months ago)
• Last Synced: 2024-11-30T13:04:14.865Z (12 days ago)
• Topics: mujoco, reinforcement-learning, robotics, simulation
• Language: Python
• Size: 2.41 MB
• Stars: 365
• Watchers: 16
• Forks: 103
• Open Issues: 21
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-model-based-RL - adroit - world](https://github.com/rlworkgroup/metaworld), [deepmind control suite](https://github.com/deepmind/dm_control) (Papers / ICLR 2023)
• awesome-simulation - mjrl - Reinforcement learning algorithms for MuJoCo tasks ([MuJoCo](https://mujoco.org))

README

        
# RL for MuJoCo

This package  contains implementations of various RL algorithms for continuous control tasks simulated with [MuJoCo.](http://www.mujoco.org/)

# Installation

The main package dependencies are `MuJoCo`, `python=3.7`, `gym>=0.13`, `mujoco-py>=2.0`, and `pytorch>=1.0`. See `setup/README.md` ([link](https://github.com/aravindr93/mjrl/tree/master/setup#installation)) for detailed install instructions.

# Bibliography

If you find the package useful, please cite the following papers.

```

@INPROCEEDINGS{Rajeswaran-NIPS-17,

    AUTHOR    = {Aravind Rajeswaran and Kendall Lowrey and Emanuel Todorov and Sham Kakade},

    TITLE     = "{Towards Generalization and Simplicity in Continuous Control}",

    BOOKTITLE = {NIPS},

    YEAR      = {2017},

}

@INPROCEEDINGS{Rajeswaran-RSS-18,

    AUTHOR    = {Aravind Rajeswaran AND Vikash Kumar AND Abhishek Gupta AND

                 Giulia Vezzani AND John Schulman AND Emanuel Todorov AND Sergey Levine},

    TITLE     = "{Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations}",

    BOOKTITLE = {Proceedings of Robotics: Science and Systems (RSS)},

    YEAR      = {2018},

}

```

# Credits

This package is maintained by [Aravind Rajeswaran](http://homes.cs.washington.edu/~aravraj/) and other members of the [Movement Control Lab,](http://homes.cs.washington.edu/~todorov/) University of Washington Seattle.