This package contains implimentations of various RL algorithms for continuous control tasks simulated with MuJoCo..
The main package dependencies are python=3.5
, gym
, mujoco-py
, and pytorch
. See setup/README.md
for detailed install instructions.
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},
}
This package is maintained by Aravind Rajeswaran and other members of the Movement Control Lab, University of Washington Seattle.