deeprlhw2.bib

@article{mnih2013playing,
  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{mnih2015human,
  title={Human-level control through deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
  journal={Nature},
  volume={518},
  number={7540},
  pages={529--533},
  year={2015},
  publisher={Nature Research}
}

@inproceedings{van2016deep,
  title={Deep Reinforcement Learning with Double Q-Learning.},
  author={Van Hasselt, Hado and Guez, Arthur and Silver, David},
  year={2016}
}

@article{wang2015dueling,
  title={Dueling network architectures for deep reinforcement learning},
  author={Wang, Ziyu and Schaul, Tom and Hessel, Matteo and van Hasselt, Hado and Lanctot, Marc and de Freitas, Nando},
  journal={arXiv preprint arXiv:1511.06581},
  year={2015}
}

@misc{linearcart,
  title = {{CartPole Linear Solvable}},
  howpublished = "\url{https://stats.stackexchange.com/questions/250531/understanding-oscillating-behaviour-when-using-q-learning-on-cart-pole-problem}",
  note = "[Online; accessed 09-March-2018]"
}