references.bib

@article{abadi2016tensorflow,
  title   = {Tensorflow: Large-scale machine learning on heterogeneous distributed systems},
  author  = {Abadi, Mart{\'\i}n and Agarwal, Ashish and Barham, Paul and Brevdo, Eugene and Chen, Zhifeng and Citro, Craig and Corrado, Greg S and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and others},
  journal = {arXiv preprint arXiv:1603.04467},
  year    = {2016}
}

@article{badrinarayanan2017segnet,
  title     = {Segnet: A deep convolutional encoder-decoder architecture for image segmentation},
  author    = {Badrinarayanan, Vijay and Kendall, Alex and Cipolla, Roberto},
  journal   = {IEEE transactions on pattern analysis and machine intelligence},
  volume    = {39},
  number    = {12},
  pages     = {2481--2495},
  year      = {2017},
  publisher = {IEEE}
}


@online{bair2019soft,
  author  = {Berkeley Artifical Intelligence Research},
  title   = {Soft Actor Critic—Deep Reinforcement Learning with Real-World Robots},
  year    = {2018},
  note    = {\url{https://bair.berkeley.edu/blog/2018/12/14/sac/}},
  urldate = {2018-12-14}
}


@article{bellemare2013arcade,
  title   = {The arcade learning environment: An evaluation platform for general agents},
  author  = {Bellemare, Marc G and Naddaf, Yavar and Veness, Joel and Bowling, Michael},
  journal = {Journal of Artificial Intelligence Research},
  volume  = {47},
  pages   = {253--279},
  year    = {2013}
}

@book{bellman2015applied,
  title     = {Applied dynamic programming},
  author    = {Bellman, Richard E and Dreyfus, Stuart E},
  volume    = {2050},
  year      = {2015},
  publisher = {Princeton university press}
}


@inproceedings{bewley2019learning,
  title        = {Learning to drive from simulation without real world labels},
  author       = {Bewley, Alex and Rigley, Jessica and Liu, Yuxuan and Hawke, Jeffrey and Shen, Richard and Lam, Vinh-Dieu and Kendall, Alex},
  booktitle    = {2019 International Conference on Robotics and Automation (ICRA)},
  pages        = {4818--4824},
  year         = {2019},
  organization = {IEEE}
}



@book{bishop2006pattern,
  title     = {Pattern recognition and machine learning},
  author    = {Bishop, Christopher M},
  year      = {2006},
  publisher = {Springer}
}

@article{brockman2016openai,
  title   = {Openai gym, 2016},
  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}
}

@online{builtin2019pytorch,
  author  = {Vihar Kurama},
  title   = {{PyTorch vs. TensorFlow: Which Framework Is Best for Your Deep Learning Project?}},
  year    = {2019},
  month   = {February},
  note    = {\url{https://builtin.com/data-science/pytorch-vs-tensorflow}},
  urldate = {2019-08-28}
}

@online{chara2018wild,
  author  = {Mohamad Charafeddine},
  title   = {{Reinforcement Learning in the Wild and Lessons Learned}},
  year    = {2018},
  note    = {\url{https://link.medium.com/SRUZ24Itx4}},
  urldate = {2018-10-26}
}

@online{cozmo2019SDK,
  author = {Anki},
  title  = {Github repository of {Cozmo SDK} written in Python},
  year   = {2019},
  note   = {\url{https://github.com/anki/cozmo-python-sdk}}
}

@inproceedings{deisenroth2011pilco,
  title     = {PILCO: A model-based and data-efficient approach to policy search},
  author    = {Deisenroth, Marc and Rasmussen, Carl E},
  booktitle = {Proceedings of the 28th International Conference on machine learning (ICML-11)},
  pages     = {465--472},
  year      = {2011}
}


@inproceedings{deng2009imagenet,
  title        = {Imagenet: A large-scale hierarchical image database},
  author       = {Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
  booktitle    = {2009 IEEE conference on computer vision and pattern recognition},
  pages        = {248--255},
  year         = {2009},
  organization = {Ieee}
}


@inproceedings{duan2016benchmarking,
  title     = {Benchmarking deep reinforcement learning for continuous control},
  author    = {Duan, Yan and Chen, Xi and Houthooft, Rein and Schulman, John and Abbeel, Pieter},
  booktitle = {International Conference on Machine Learning},
  pages     = {1329--1338},
  year      = {2016}
}

@article{duchi2011adaptive,
  title   = {Adaptive subgradient methods for online learning and stochastic optimization},
  author  = {Duchi, John and Hazan, Elad and Singer, Yoram},
  journal = {Journal of Machine Learning Research},
  volume  = {12},
  number  = {Jul},
  pages   = {2121--2159},
  year    = {2011}
}

@article{erhan2009visualizing,
  title   = {Visualizing higher-layer features of a deep network},
  author  = {Erhan, Dumitru and Bengio, Yoshua and Courville, Aaron and Vincent, Pascal},
  journal = {University of Montreal},
  volume  = {1341},
  number  = {3},
  pages   = {1},
  year    = {2009}
}
@article{fox2015taming,
  title   = {Taming the noise in reinforcement learning via soft updates},
  author  = {Fox, Roy and Pakman, Ari and Tishby, Naftali},
  journal = {arXiv preprint arXiv:1512.08562},
  year    = {2015}
}

@article{franccois2018introduction,
  title     = {An introduction to deep reinforcement learning},
  author    = {Fran{\c{c}}ois-Lavet, Vincent and Henderson, Peter and Islam, Riashat and Bellemare, Marc G and Pineau, Joelle and others},
  journal   = {Foundations and Trends{\textregistered} in Machine Learning},
  volume    = {11},
  number    = {3-4},
  pages     = {219--354},
  year      = {2018},
  publisher = {Now Publishers, Inc.}
}

@article{fujimoto2018addressing,
  title   = {Addressing function approximation error in actor-critic methods},
  author  = {Fujimoto, Scott and van Hoof, Herke and Meger, David},
  journal = {arXiv preprint arXiv:1802.09477},
  year    = {2018}
}


@inproceedings{glorot2010understanding,
  title     = {Understanding the difficulty of training deep feedforward neural networks},
  author    = {Glorot, Xavier and Bengio, Yoshua},
  booktitle = {Proceedings of the thirteenth international conference on artificial intelligence and statistics},
  pages     = {249--256},
  year      = {2010}
}


@inproceedings{gu2017deep,
  title        = {Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates},
  author       = {Gu, Shixiang and Holly, Ethan and Lillicrap, Timothy and Levine, Sergey},
  booktitle    = {2017 IEEE international conference on robotics and automation (ICRA)},
  pages        = {3389--3396},
  year         = {2017},
  organization = {IEEE}
}

@inproceedings{haarnoja2017reinforcement,
  title        = {Reinforcement learning with deep energy-based policies},
  author       = {Haarnoja, Tuomas and Tang, Haoran and Abbeel, Pieter and Levine, Sergey},
  booktitle    = {Proceedings of the 34th International Conference on Machine Learning-Volume 70},
  pages        = {1352--1361},
  year         = {2017},
  organization = {JMLR. org}
}

@article{haarnoja2018alg,
  title   = {Soft actor-critic algorithms and applications},
  author  = {Haarnoja, Tuomas and Zhou, Aurick and Hartikainen, Kristian and Tucker, George and Ha, Sehoon and Tan, Jie and Kumar, Vikash and Zhu, Henry and Gupta, Abhishek and Abbeel, Pieter and others},
  journal = {arXiv preprint arXiv:1812.05905},
  year    = {2018}
}

@article{haarnoja2018soft,
  title   = {Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor},
  author  = {Haarnoja, Tuomas and Zhou, Aurick and Abbeel, Pieter and Levine, Sergey},
  journal = {arXiv preprint arXiv:1801.01290},
  year    = {2018}
}


@incollection{hasselt2010double,
  title     = {Double Q-learning},
  author    = {Hado V. Hasselt},
  booktitle = {Advances in Neural Information Processing Systems 23},
  editor    = {J. D. Lafferty and C. K. I. Williams and J. Shawe-Taylor and R. S. Zemel and A. Culotta},
  pages     = {2613--2621},
  year      = {2010},
  publisher = {Curran Associates, Inc.},
  url       = {http://papers.nips.cc/paper/3964-double-q-learning.pdf}
}

@article{hawke2019urban,
  title   = {Urban Driving with Conditional Imitation Learning},
  author  = {Hawke, Jeffrey and Shen, Richard and Gurau, Corina and Sharma, Siddharth and Reda, Daniele and Nikolov, Nikolay and Mazur, Przemyslaw and Micklethwaite, Sean and Griffiths, Nicolas and Shah, Amar and others},
  journal = {arXiv preprint arXiv:1912.00177},
  year    = {2019}
}
@inproceedings{henderson2018deep,
  title     = {Deep reinforcement learning that matters},
  author    = {Henderson, Peter and Islam, Riashat and Bachman, Philip and Pineau, Joelle and Precup, Doina and Meger, David},
  booktitle = {Thirty-Second AAAI Conference on Artificial Intelligence},
  year      = {2018}
}

@inproceedings{hessel2018rainbow,
  title     = {Rainbow: Combining improvements in deep reinforcement learning},
  author    = {Hessel, Matteo and Modayil, Joseph and Van Hasselt, Hado and Schaul, Tom and Ostrovski, Georg and Dabney, Will and Horgan, Dan and Piot, Bilal and Azar, Mohammad and Silver, David},
  booktitle = {Thirty-Second AAAI Conference on Artificial Intelligence},
  year      = {2018}
}

@article{huval2015empirical,
  title   = {An empirical evaluation of deep learning on highway driving},
  author  = {Huval, Brody and Wang, Tao and Tandon, Sameep and Kiske, Jeff and Song, Will and Pazhayampallil, Joel and Andriluka, Mykhaylo and Rajpurkar, Pranav and Migimatsu, Toki and Cheng-Yue, Royce and others},
  journal = {arXiv preprint arXiv:1504.01716},
  year    = {2015}
}

@online{ingredientsRoboticsResearch,
  author = {  Plappert, Matthias and Andrychowicz, Marcin and Ray, Alex and McGrew, Bob and  Baker, Bowen and Powell, Glenn and Schneider, Jonas and Tobin, Josh and Chociej, Maciek and Welinder, Peter and Kumar, Vikash and Zaremba, Wojciech},
  title  = {Ingredients for	Robotics Research},
  editor = {OpenAI blog},
  month  = {February},
  year   = {2018},
  url    = {\url{https://openai.com/blog/ingredients-for-robotics-research/}},
  note   = {\url{https://openai.com/blog/ingredients-for-robotics-research/}}
}

@article{ioffe2015batch,
  title   = {Batch normalization: Accelerating deep network training by reducing internal covariate shift},
  author  = {Ioffe, Sergey and Szegedy, Christian},
  journal = {arXiv preprint arXiv:1502.03167},
  year    = {2015}
}

@article{kendall2018learning,
  title   = {Learning to Drive in a Day},
  author  = {Kendall, Alex and Hawke, Jeffrey and Janz, David and Mazur, Przemyslaw and Reda, Daniele and Allen, John-Mark and Lam, Vinh-Dieu and Bewley, Alex and Shah, Amar},
  journal = {arXiv preprint arXiv:1807.00412},
  year    = {2018}
}

@inproceedings{kendall2019learning,
  title        = {Learning to drive in a day},
  author       = {Kendall, Alex and Hawke, Jeffrey and Janz, David and Mazur, Przemyslaw and Reda, Daniele and Allen, John-Mark and Lam, Vinh-Dieu and Bewley, Alex and Shah, Amar},
  booktitle    = {2019 International Conference on Robotics and Automation (ICRA)},
  pages        = {8248--8254},
  year         = {2019},
  organization = {IEEE}
}

@online{kendall2019nowisthetime,
  author = {Alex Kendall},
  title  = {{Now is the Time for Reinforcement Learning on Real Robots}},
  year   = {2019},
  note   = {\url{https://alexgkendall.com/reinforcement\_learning/now\_is\_the\_time\_for\_reinforcement\_learning\_on\_real\_robots/}}
}

@article{kingma2013auto,
  title   = {Auto-encoding variational bayes},
  author  = {Kingma, Diederik P and Welling, Max},
  journal = {arXiv preprint arXiv:1312.6114},
  year    = {2013}
}

@article{kingma2014adam,
  title   = {Adam: A method for stochastic optimization},
  author  = {Kingma, Diederik P and Ba, Jimmy},
  journal = {arXiv preprint arXiv:1412.6980},
  year    = {2014}
}

@inproceedings{konda2000actor,
  title     = {Actor-critic algorithms},
  author    = {Konda, Vijay R and Tsitsiklis, John N},
  booktitle = {Advances in neural information processing systems},
  pages     = {1008--1014},
  year      = {2000}
}

@article{kullback1951information,
  title     = {On information and sufficiency},
  author    = {Kullback, Solomon and Leibler, Richard A},
  journal   = {The annals of mathematical statistics},
  volume    = {22},
  number    = {1},
  pages     = {79--86},
  year      = {1951},
  publisher = {JSTOR}
}

@techreport{kullback1959information,
  title  = {Information theory and statistics},
  author = {Kullback, Solomon},
  year   = {1959}
}

@book{lapan2018deep,
  title     = {Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more},
  author    = {Lapan, Maxim},
  year      = {2018},
  publisher = {Packt Publishing Ltd}
}

@article{lecun1995convolutional,
  title   = {Convolutional networks for images, speech, and time series},
  author  = {LeCun, Yann and Bengio, Yoshua and others},
  journal = {The handbook of brain theory and neural networks},
  volume  = {3361},
  number  = {10},
  pages   = {1995},
  year    = {1995}
}

@article{lecun1998gradient,
  title     = {Gradient-based learning applied to document recognition},
  author    = {LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick and others},
  journal   = {Proceedings of the IEEE},
  volume    = {86},
  number    = {11},
  pages     = {2278--2324},
  year      = {1998},
  publisher = {Taipei, Taiwan}
}

@article{lecun2015deep,
  title     = {Deep learning},
  author    = {LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
  journal   = {nature},
  volume    = {521},
  number    = {7553},
  pages     = {436},
  year      = {2015},
  publisher = {Nature Publishing Group}
}

@article{lillicrap2015continuous,
  title   = {Continuous control with deep reinforcement learning},
  author  = {Lillicrap, Timothy P and Hunt, Jonathan J and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan},
  journal = {arXiv preprint arXiv:1509.02971},
  year    = {2015}
}

@article{lin1992self,
  title     = {Self-improving reactive agents based on reinforcement learning, planning and teaching},
  author    = {Lin, Long-Ji},
  journal   = {Machine learning},
  volume    = {8},
  number    = {3-4},
  pages     = {293--321},
  year      = {1992},
  publisher = {Springer}
}

@online{mellon2017cognitive,
  author  = {{Carnegie Mellon University}},
  title   = {{15-494/694}: Cognitive Robotics},
  year    = {2019},
  note    = {\url{http://www.cs.cmu.edu/afs/cs/academic/class/15494-s17/}},
  urldate = {2019-07-29}
}

@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},
  year      = {2015},
  publisher = {Nature Publishing Group}
}
@inproceedings{mnih2016asynchronous,
  title     = {Asynchronous methods for deep reinforcement learning},
  author    = {Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
  booktitle = {International conference on machine learning},
  pages     = {1928--1937},
  year      = {2016}
}

@online{openai2018dota,
  author  = {OpenAI},
  title   = {{OpenAI Five}},
  year    = {2018},
  note    = {\url{https://openai.com/blog/openai-five/}},
  urldate = {2018-06-25}
}

@online{openai2018spinningup,
  author  = {OpenAI},
  title   = {{OpenAI} {Spinning Up}},
  year    = {2019},
  note    = {\url{https://spinningup.openai.com/en/latest/}},
  urldate = {2019-07-29}
}

@online{openai2019dota,
  author  = {OpenAI},
  title   = {How to Train Your {OpenAI Five}},
  year    = {2019},
  note    = {\url{https://openai.com/blog/how-to-train-your-openai-five/}},
  urldate = {2019-04-15}
}

@online{openaigymdocs,
  author  = {OpenAI},
  title   = {{OpenAI} {Gym} Documentation},
  year    = {2016},
  note    = {\url{https://gym.openai.com/docs/}},
  urldate = {2019-07-29}
}

@online{openaigymgithub,
  author  = {OpenAI},
  title   = {{OpenAI} Gym},
  year    = {2016},
  note    = {\url{https://github.com/openai/gym}},
  urldate = {2019-07-29}
}

@inproceedings{ort2018autonomous,
  title        = {Autonomous vehicle navigation in rural environments without detailed prior maps},
  author       = {Ort, Teddy and Paull, Liam and Rus, Daniela},
  booktitle    = {2018 IEEE International Conference on Robotics and Automation (ICRA)},
  pages        = {2040--2047},
  year         = {2018},
  organization = {IEEE}
}

@article{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},
  year   = {2017}
}

@online{raffin2019learning,
  author  = {Raffin, Antonin},
  title   = {{Learning to Drive Smoothly in Minutes}},
  editor  = {{Towards Data Science}},
  month   = {January},
  year    = {2019},
  url     = {\url{https://towardsdatascience.com/learning-to-drive-smoothly-in-minutes-450a7cdb35f4}},
  note    = {\url{https://towardsdatascience.com/learning-to-drive-smoothly-in-minutes-450a7cdb35f4}},
  urldate = {2019-01-27}
}


@inproceedings{rawlik2013stochastic,
  title     = {On stochastic optimal control and reinforcement learning by approximate inference},
  author    = {Rawlik, Konrad and Toussaint, Marc and Vijayakumar, Sethu},
  booktitle = {Twenty-Third International Joint Conference on Artificial Intelligence},
  year      = {2013}
}

@article{rezende2014stochastic,
  title   = {Stochastic backpropagation and approximate inference in deep generative models},
  author  = {Rezende, Danilo Jimenez and Mohamed, Shakir and Wierstra, Daan},
  journal = {arXiv preprint arXiv:1401.4082},
  year    = {2014}
}

@article{rumelhart1988learning,
  title   = {Learning representations by back-propagating errors},
  author  = {Rumelhart, David E and Hinton, Geoffrey E and Williams, Ronald J and others},
  journal = {Cognitive modeling},
  volume  = {5},
  number  = {3},
  pages   = {1},
  year    = {1988}
}

@article{schaul2015prioritized,
  title   = {Prioritized experience replay},
  author  = {Schaul, Tom and Quan, John and Antonoglou, Ioannis and Silver, David},
  journal = {arXiv preprint arXiv:1511.05952},
  year    = {2015}
}

@article{schulman2017proximal,
  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}
}

@book{shalev2014understanding,
  title     = {Understanding machine learning: From theory to algorithms},
  author    = {Shalev-Shwartz, Shai and Ben-David, Shai},
  year      = {2014},
  publisher = {Cambridge university press}
}
@inproceedings{silver2014deterministic,
  title  = {Deterministic policy gradient algorithms},
  author = {Silver, David and Lever, Guy and Heess, Nicolas and Degris, Thomas and Wierstra, Daan and Riedmiller, Martin},
  year   = {2014}
}

@unpublished{silver2015lectures,
  author      = {David Silver},
  institution = {University College London},
  year        = {2015},
  title       = {{University College London Course on Reinforcement Learning}},
  note        = {\url{http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html}}
}

@article{silver2016mastering,
  title     = {Mastering the game of Go with deep neural networks and tree search},
  author    = {Silver, David and Huang, Aja and Maddison, Chris J and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},
  journal   = {nature},
  volume    = {529},
  number    = {7587},
  pages     = {484},
  year      = {2016},
  publisher = {Nature Publishing Group}
}
@article{silver2017mastering,
  title   = {Mastering chess and shogi by self-play with a general reinforcement learning algorithm},
  author  = {Silver, David and Hubert, Thomas and Schrittwieser, Julian and Antonoglou, Ioannis and Lai, Matthew and Guez, Arthur and Lanctot, Marc and Sifre, Laurent and Kumaran, Dharshan and Graepel, Thore and others},
  journal = {arXiv preprint arXiv:1712.01815},
  year    = {2017}
}

@article{springenberg2014striving,
  title   = {Striving for simplicity: The all convolutional net},
  author  = {Springenberg, Jost Tobias and Dosovitskiy, Alexey and Brox, Thomas and Riedmiller, Martin},
  journal = {arXiv preprint arXiv:1412.6806},
  year    = {2014}
}

@online{stanford2019cs231n,
  author  = {{Stanford University}},
  title   = {{CS231n}: Convolutional Neural Networks for Visual Recognition},
  year    = {2019},
  note    = {\url{http://cs231n.github.io/}},
  urldate = {2019-07-29}
}

@book{sutton2018reinforcement,
  title     = {Reinforcement learning: An introduction},
  author    = {Sutton, Richard S and Barto, Andrew G},
  year      = {2018},
  publisher = {MIT press}
}

@article{tieleman2012lecture,
  title   = {Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude},
  author  = {Tieleman, Tijmen and Hinton, Geoffrey},
  journal = {COURSERA: Neural networks for machine learning},
  volume  = {4},
  number  = {2},
  pages   = {26--31},
  year    = {2012}
}

@inproceedings{todorov2012mujoco,
  title        = {Mujoco: A physics engine for model-based control},
  author       = {Todorov, Emanuel and Erez, Tom and Tassa, Yuval},
  booktitle    = {2012 IEEE/RSJ International Conference on Intelligent Robots and Systems},
  pages        = {5026--5033},
  year         = {2012},
  organization = {IEEE}
}

@online{touretzky2018cozmopedia,
  author  = {Touretzky, Dave},
  title   = {{Cozmopedia Wiki}},
  year    = {2018},
  note    = {\url{https://github.com/touretzkyds/cozmopedia/wiki}},
  urldate = {2019-07-29}
}

@inproceedings{toussaint2009robot,
  title        = {Robot trajectory optimization using approximate inference},
  author       = {Toussaint, Marc},
  booktitle    = {Proceedings of the 26th annual international conference on machine learning},
  pages        = {1049--1056},
  year         = {2009},
  organization = {ACM}
}

@article{uhlenbeck1930theory,
  title     = {On the theory of the Brownian motion},
  author    = {Uhlenbeck, George E and Ornstein, Leonard S},
  journal   = {Physical review},
  volume    = {36},
  number    = {5},
  pages     = {823},
  year      = {1930},
  publisher = {APS}
}


@inproceedings{van2016deep,
  title     = {Deep reinforcement learning with double q-learning},
  author    = {Van Hasselt, Hado and Guez, Arthur and Silver, David},
  booktitle = {Thirtieth AAAI conference on artificial intelligence},
  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}
}

@article{watkins1989learning,
  title     = {Learning from delayed rewards},
  author    = {Watkins, Christopher John Cornish Hellaby},
  year      = {1989},
  publisher = {King's College, Cambridge}
}

@online{wayve2019human,
  author  = {WAYVE},
  title   = {Learning to Drive like a Human},
  month   = {April},
  year    = {2019},
  note    = {\url{https://wayve.ai/blog/driving-like-human}},
  urldate = {2019-04-03}
}

@online{wayve2019learned,
  author  = {WAYVE},
  title   = {Learned Urban Driving},
  year    = {2019},
  month   = {December},
  note    = {\url{https://wayve.ai/blog/learned-urban-driving}},
  urldate = {2019-12-02}
}

@article{ziebart2008maximum,
  title     = {Maximum entropy inverse reinforcement learning},
  author    = {Ziebart, Brian D and Maas, Andrew and Bagnell, J Andrew and Dey, Anind K},
  year      = {2008},
  publisher = {figshare}
}