RL for MuJoCo

This package contains implimentations of various RL algorithms for continuous control tasks simulated with MuJoCo..

Installation

The main package dependencies are python=3.5, gym, mujoco-py, and pytorch. See setup/README.md for detailed install instructions.

Bibliography

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

@inproceedings{Rajeswaran17generalization, 
    title = "{Towards Generalization and Simplicity in Continuous Control}",
    author = {Aravind Rajeswaran and Kendall Lowrey and Emanuel Todorov and Sham Kakade},
    booktitle = {NIPS},
    year = {2017},
}

@article{Rajeswaran17dexterous,
    title = "{Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations}",
    author = {Aravind Rajeswaran and Vikash Kumar and Abhishek Gupta and John Schulman and Emanuel Todorov and Sergey Levine},
    journal = {CoRR},
    volume = {abs/1709.10087},
    year = {2017},
}

Credits

This package is maintained by Aravind Rajeswaran and other members of the Movement Control Lab, University of Washington Seattle.