doerlbh / hrl-ep3

Code for our paper: Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies

hrl-ep3

Code for our paper: Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies

Citation

If you find this work helpful, please cite our work, as well as Ilya Kostrikov's pytoch baseline repo.

@article{marino2019ep3,
  title={Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies},
  author={Marino, Kenneth and Gupta, Abhinav and Fergus, Rob and Szlam, Arthur},
  journal={ICLR},
  year={2019}
}

Requirements

• Python 3
• PyTorch
• Visdom
• OpenAI baselines

Acknowledgements

This repo was initially copied from Ilya Kostrikov's pytorch baseline repo https://github.com/ikostrikov/pytorch-a2c-ppo-acktr . We will modify many of the original files and add new ones as is useful. We also will continue to use this as our baselines. See their github for more documentation on the baselines. Please also cite this repository in your publications if you make use of this code:

@misc{pytorchrl,
  author = {Kostrikov, Ilya},
  title = {PyTorch Implementations of Reinforcement Learning Algorithms},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/ikostrikov/pytorch-a2c-ppo-acktr}},
}