paper.bib

@misc{sutton:1998,
  title={Introduction to reinforcement learning. Vol. 135},
  author={Sutton, Richard S and Barto, Andrew G},
  year={1998},
  publisher={Cambridge: MIT press}
}

@article{dhariwal:2017,
  title={Openai baselines},
  author={Dhariwal, Prafulla and Hesse, Christopher and Klimov, Oleg and Nichol, Alex and Plappert, Matthias and Radford, Alec and Schulman, John and Sidor, Szymon and Wu, Yuhuai and Zhokhov, Peter},
  url={https://github.com/openai/baselines},
  year={2017}
}

@article{schaarschmidt:2017,
  title={Tensorforce: A tensorflow library for applied reinforcement learning},
  author={Schaarschmidt, Michael and Kuhnle, Alexander and Fricke, Kai},
  url={https://github.com/tensorflow/tensorflow},
  year={2017}
}

@article{liang:2017,
  title={Ray rllib: A composable and scalable reinforcement learning library},
  author={Liang, Eric and Liaw, Richard and Nishihara, Robert and Moritz, Philipp and Fox, Roy and Gonzalez, Joseph and Goldberg, Ken and Stoica, Ion},
  journal={arXiv preprint arXiv:1712.09381},
  year={2017}
}

@article{caspi:2017,
  title={Reinforcement Learning Coach.(Dec. 2017)},
  author={Caspi, Itai and Leibovich, Gal and Novik, Gal},
  doi={10.5281/zenodo.1134899},
  url={https://doi.org/10.5281/zenodo.1134899},
  volume={1134899},
  year={2017}
}

@inproceedings{abadi:2016,
  title={Tensorflow: A system for large-scale machine learning},
  author={Abadi, Mart{\'\i}n and Barham, Paul and Chen, Jianmin and Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and Isard, Michael and others},
  booktitle={12th USENIX Symposium on Operating Systems Design and Implementation OSDI 16)},
  pages={265--283},
  year={2016}
}

@article{brockman:2016,
  title={Openai gym},
  author={Brockman, Greg and Cheung, Vicki and Pettersson, Ludwig and Schneider, Jonas and Schulman, John and Tang, Jie and Zaremba, Wojciech},
  journal={arXiv preprint arXiv:1606.01540},
  year={2016}
}

@misc{kerasrl:2019, title={keras-rl/keras-rl}, url={https://github.com/keras-rl/keras-rl}, journal={GitHub}, author={Matthias Plappert}, year={2019}, month={Mar}}

@article{castro:2018,
  title={Dopamine: A research framework for deep reinforcement learning},
  author={Castro, Pablo Samuel and Moitra, Subhodeep and Gelada, Carles and Kumar, Saurabh and Bellemare, Marc G},
  journal={arXiv preprint arXiv:1812.06110},
  year={2018}
}

@article{mnih:2013,
  title={Playing atari with deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Graves, Alex and Antonoglou, Ioannis and Wierstra, Daan and Riedmiller, Martin},
  journal={arXiv preprint arXiv:1312.5602},
  year={2013}
}

@article{plappert:2017,
  title={Parameter space noise for exploration},
  author={Plappert, Matthias and Houthooft, Rein and Dhariwal, Prafulla and Sidor, Szymon and Chen, Richard Y and Chen, Xi and Asfour, Tamim and Abbeel, Pieter and Andrychowicz, Marcin},
  journal={arXiv preprint arXiv:1706.01905},
  year={2017}
}

@incollection{sutton2000,
  title = {Policy Gradient Methods for Reinforcement Learning with Function Approximation},
  author = {Sutton, Richard S and David A. McAllester and Satinder P. Singh and Mansour, Yishay},
  booktitle = {{Advances in Neural Information Processing Systems 12}},
  editor = {S. A. Solla and T. K. Leen and K. M\"{u}ller},
  pages = {1057--1063},
  year = {2000},
  publisher = {MIT Press},
}

@inproceedings{silver2014deterministic,
  title = 	 {Deterministic Policy Gradient Algorithms},
  author = 	 {David Silver and Guy Lever and Nicolas Heess and Thomas Degris and Daan Wierstra and Martin Riedmiller},
  booktitle = 	 {{Proceedings of the 31st International Conference on Machine Learning}},
  pages = 	 {387--395},
  year = 	 {2014},
  editor = 	 {Eric P. Xing and Tony Jebara},
  volume = 	 {32},
  number =       {1},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Bejing, China},
  month = 	 {22--24 Jun},
  publisher = 	 {{PMLR}},
  url = 	 {http://proceedings.mlr.press/v32/silver14.html},
}

@article{schulman:2017,
  title={Proximal policy optimization algorithms},
  author={Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg},
  journal={arXiv preprint arXiv:1707.06347},
  year={2017}
}

@article{savva:2019,
  title={Habitat: A platform for embodied ai research},
  author={Savva, Manolis and Kadian, Abhishek and Maksymets, Oleksandr and Zhao, Yili and Wijmans, Erik and Jain, Bhavana and Straub, Julian and Liu, Jia and Koltun, Vladlen and Malik, Jitendra and others},
  journal={arXiv preprint arXiv:1904.01201},
  year={2019}
}

@article{chen:2018,
  title={Bayesian optimization in alphago},
  author={Chen, Yutian and Huang, Aja and Wang, Ziyu and Antonoglou, Ioannis and Schrittwieser, Julian and Silver, David and de Freitas, Nando},
  journal={arXiv preprint arXiv:1812.06855},
  year={2018}
}

@inproceedings{ha:2018,
  title={Recurrent world models facilitate policy evolution},
  author={Ha, David and Schmidhuber, J{\"u}rgen},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2450--2462},
  year={2018}
}

@misc{TFAgents,
  title={TF-Agents: A library for Reinforcement Learning in TensorFlow},
  author={Sergio Guadarrama, Anoop Korattikara, Oscar Ramirez,
    Pablo Castro, Ethan Holly, Sam Fishman, Ke Wang, Ekaterina Gonina, Neal Wu,
    Chris Harris, Vincent Vanhoucke, Eugene Brevdo},
  url={"https://github.com/tensorflow/agents"},
  year={2018}
}

@misc{hill:2019, 
  title={hill-a/stable-baselines}, 
  url={https://github.com/hill-a/stable-baselines}, 
  author={Hill}, 
  year={2019}, 
  month={Jun}
}

@inproceedings{paszke2017automatic,
  title={Automatic Differentiation in PyTorch},
  author={Paszke, Adam and Gross, Sam and Chintala, Soumith and Chanan, Gregory and Yang, Edward and DeVito, Zachary and Lin, Zeming and Desmaison, Alban and Antiga, Luca and Lerer, Adam},
  booktitle={NIPS Autodiff Workshop},
  year={2017}
}