</dt-appendix>

</body>

<script type="text/bibliography">

@online{ forrester,

author = "Forrester, Jay Wright",

title = "Counterintuitive behavior of social systems",

publisher = "Technology Review",

year = "1971",

url = "https://en.wikipedia.org/wiki/Mental_model",

note = "[Online; accessed 01-Nov-2017]"

}

@online{ video_game_exploits,

author = "Wikipedia, Authors",

publisher = "Wikipedia",

title = "Video Game Exploits",

year = "2017",

url = "https://en.wikipedia.org/wiki/Video_game_exploits",

note = "[Online; accessed 01-Nov-2017]"

}

@article{facial_identity_primate_brain,

author = {Cheang, L. and Tsao, D.},

title = "The Code for Facial Identity in the Primate Brain",

journal = {Cell},

year = {2017},

url = "http://www.cell.com/cell/fulltext/S0092-8674%2817%2930538-X",

doi = "10.1016/j.cell.2017.05.011",

}

@article{ single_neuron_viz,

author = "Quiroga, R. and Reddy, L. and Kreiman, G. and Koch, C. and Fried, I.",

title = "Invariant visual representation by single neurons in the human brain",

year = "2005",

journal = "Nature",

url = "http://www.nature.com/nature/journal/v435/n7045/abs/nature03687.html",

doi = "10.1038/nature03687",

}

@article{primary_viz_cortex_past_present,

author = {Nortmann, Nora and Rekauzke, Sascha and Onat, Selim and König, Peter and Jancke, Dirk},

title = {Primary Visual Cortex Represents the Difference Between Past and Present},

journal = {Cerebral Cortex},

volume = {25},

number = {6},

pages = {1427-1440},

year = {2015},

doi = {10.1093/cercor/bht318},

URL = {http://dx.doi.org/10.1093/cercor/bht318},

}

@article{ mt_motion,

author = "Gerrit, M. and Fischer, J. and Whitney, D.",

journal = "Neuron",

title = "Motion-Dependent Representation of Space in Area MT+",

year = "2013",

url = "http://dx.doi.org/10.1016/j.neuron.2013.03.010",

doi = "10.1016/j.neuron.2013.03.010"

}

@misc{ mt_motion_article,

author = "Hirshon, B.",

title = "Tracking Fastballs",

publisher = "Science Update Interview",

year = "2013",

url = "http://sciencenetlinks.com/science-news/science-updates/tracking-fastballs/",

}

@misc{ survival_optimization,

author = "Mobbs, Dean and Hagan, Cindy C. and Dalgleish, Tim and Silston, Brian and Prévost, Charlotte",

title = "The ecology of human fear: survival optimization and the nervous system.",

journal = "Frontiers in Neuroscience",

year = "2015",

url = "https://www.frontiersin.org/article/10.3389/fnins.2015.00055",

doi = "10.3389/fnins.2015.00055",

}

@online{tanaka_fastball,

author = {Channel ESPN},

title = {Sport Science: Masahiro Tanaka},

year = 2017,

url = {https://youtu.be/ZEtZGmMxwaw},

urldate = {2017-11-01}

}

@misc{ flappy_bird,

author = "Dong Nguyen",

publisher = "dotGEARS",

title = "Flappy Bird",

year = "2013",

url = "https://en.wikipedia.org/wiki/Flappy_Bird",

note = "[Online; accessed 01-Nov-2017]"

}

@misc{ flappy_bird_clone,

author = "Sourabh Verma",

publisher = "GitHub",

title = "A Flappy Bird Clone using python-pygame",

year = "2013",

url = "https://github.com/sourabhv/FlapPyBird",

note = "[Online; accessed 01-Nov-2017]"

}

@misc{ flappy_bird_ne,

author = "Vincent Bazia",

publisher = "GitHub",

title = "Program learning to play Flappy Bird by machine learning",

year = "2016",

url = "https://github.com/xviniette/FlappyLearning",

note = "[Online; accessed 01-Nov-2017]"

}

@article{learning_to_think,

title={On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models},

author={Schmidhuber, Jürgen},

journal={ArXiv preprint},

year={2015},

url={https://arxiv.org/abs/1511.09249}

}

@ARTICLE{rl_survey,

author={K. Arulkumaran and M. P. Deisenroth and M. Brundage and A. A. Bharath},

journal={IEEE Signal Processing Magazine},

title={Deep Reinforcement Learning: A Brief Survey},

year={2017},

volume={34},

number={6},

pages={26-38},

keywords={Artificial intelligence;Learning (artificial intelligence);Machine learning;Neural networks;Signal processing algorithms;Visualization},

doi={10.1109/MSP.2017.2743240},

ISSN={1053-5888},

month={Nov},

url={https://arxiv.org/abs/1708.05866}

}

@online{carracing_v0,

author = {Oleg Klimov},

title = {CarRacing-v0},

year = 2016,

url = {https://gym.openai.com/envs/CarRacing-v0/},

urldate = {2017-11-01}

}

@article{carracing_cs234,

title={Reinforcement Car Racing with A3C},

author = {Jang, S. and Min, J. and Lee, C.},

year={2017},

url="https://www.scribd.com/document/358019044/Reinforcement-Car-Racing-with-A3C"

}

@article{carracing_cs221,

title={Car Racing using Reinforcement Learning},

author = {Khan, M. and Elibol, O.},

year={2016},

url="https://web.stanford.edu/class/cs221/2017/restricted/p-final/elibol/final.pdf"

}

@article{mdnrnn_tutorial,

title={Recurrent Neural Network Tutorial for Artists},

author = {Ha, D.},

journal={blog.otoro.net},

year={2017},

url="http://blog.otoro.net/2017/01/01/recurrent-neural-network-artist/"

}

@article{openai,

title={Evolution Strategies as a Scalable Alternative to Reinforcement Learning},

author = {Salimans, T. and Ho, J. and Chen, X. and Sidor, S. and Sutskever, I.},

journal={ArXiv preprint},

year={2017},

url={https://arxiv.org/abs/1703.03864}

}

@article{visuales,

title={A Visual Guide to Evolution Strategies},

author = {Ha, D.},

journal={blog.otoro.net},

year={2017},

url="http://blog.otoro.net/2017/10/29/visual-evolution-strategies/"

}

@article{stablees,

title={Evolving Stable Strategies},

author = {Ha, D.},

journal={blog.otoro.net},

year={2017},

url="http://blog.otoro.net/2017/11/12/evolving-stable-strategies/"

}

@article{cmaes_original,

author = {Hansen, Nikolaus and Ostermeier, Andreas},

title = {Completely Derandomized Self-Adaptation in Evolution Strategies},

journal = {Evolutionary Computation},

issue_date = {June 2001},

volume = {9},

number = {2},

month = jun,

year = {2001},

issn = {1063-6560},

pages = {159--195},

numpages = {37},

url = {http://www.cmap.polytechnique.fr/~nikolaus.hansen/cmaartic.pdf},

doi = {10.1162/106365601750190398},

acmid = {1108843},

publisher = {MIT Press},

address = {Cambridge, MA, USA},

}

@article{cmaes,

title={The CMA Evolution Strategy: A Tutorial},

author = {Hansen, N.},

journal={ArXiv preprint},

year={2016},

url={https://arxiv.org/abs/1604.00772}

}

@article{sampling_generative_networks,

title={Sampling Generative Networks},

author = {White, T.},

journal={ArXiv preprint},

year={2016},

url={https://arxiv.org/abs/1609.04468}

}

@article{vae,

title={Auto-Encoding Variational Bayes},

author = {Kingma, D. and Welling, M.},

journal={ArXiv preprint},

year={2013},

url={https://arxiv.org/abs/1312.6114}

}

@article{vae_dm,

title={Stochastic Backpropagation and Approximate Inference in Deep Generative Models},

author = {Jimenez Rezende, D. and Mohamed, S. and Wierstra, D.},

journal={ArXiv preprint},

year={2014},

url={https://arxiv.org/abs/1401.4082}

}

@BOOK{understandingcomics,

TITLE = {Understanding Comics: The Invisible Art},

AUTHOR = {McCloud, Scott},

YEAR = {1993},

PUBLISHER = {Tundra Publishing},

url = "https://en.wikipedia.org/wiki/Understanding_Comics",

}

@online{understandingcomics_blog,

TITLE = "More thoughts from Understanding Comics by Scott McCloud",

AUTHOR = {E, M.},

YEAR = {2012},

PUBLISHER = {Tumblr},

url = "http://memeengine.tumblr.com/post/28333277260/more-thoughts-from-understanding-comics-by-scott",

}

@online{browser_car,

author = {Jan Hünermann},

title = {Self-driving cars in the browser},

year = 2017,

url = {http://janhuenermann.com/projects/learning-to-drive},

urldate = {2017-11-01}

}

@online{keras_car,

author = {Ben Lau},

title = {Using Keras and Deep Deterministic Policy Gradient to play TORCS},

year = 2016,

url = {https://yanpanlau.github.io/2016/10/11/Torcs-Keras.html},

urldate = {2017-11-01}

}

@online{keras_flappybird,

author = {Ben Lau},

title = {Using Keras and Deep Q-Network to Play FlappyBird},

year = 2016,

url = {https://yanpanlau.github.io/2016/07/10/FlappyBird-Keras.html},

urldate = {2017-11-01}

}

@inproceedings{vizdoom,

author = {Michael Kempka and Marek Wydmuch and Grzegorz Runc and Jakub Toczek and Wojciech Jaskowski},

title = {ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning},

booktitle = {IEEE Conference on Computational Intelligence and Games},

year = {2016},

url = {http://arxiv.org/abs/1605.02097},

address = {Santorini, Greece},

Month = {Sep},

Pages = {341--348},

Publisher = {IEEE},

Note = {The best paper award}

}

@online{takecover,

author = {Philip Paquette},

title = {DoomTakeCover-v0},

year = 2016,

url = {https://gym.openai.com/envs/DoomTakeCover-v0/},

urldate = {2017-11-01}

}

@online{mar_io_kart,

author = {Seth Bling},

title = "Mar I/O Kart",

year = 2015,

url = {https://youtu.be/S9Y_I9vY8Qw},

urldate = {2017-11-01}

}

@ARTICLE{bishop,

journal = {Technical Report},

title = {Mixture density networks},

author = {Christopher M. Bishop},

address = {Birmingham},

publisher = {Aston University},

url = {http://publications.aston.ac.uk/373/},

year = 1994,

}

@article{mdntf,

title={Mixture Density Networks with TensorFlow},

author={Ha, D.},

journal={blog.otoro.net},

url = "http://blog.otoro.net/2015/11/24/mixture-density-networks-with-tensorflow/",

year={2015}

}

@article{graves_rnn,

title={Generating sequences with recurrent neural networks},

author={Graves, Alex},

journal={ArXiv preprint},

url = {https://arxiv.org/abs/1308.0850},

year={2013}

}

@ARTICLE{sketchrnn,

author = {Ha, D. and Eck, D.},

title = "A Neural Representation of Sketch Drawings",

journal={ArXiv preprint},

year = 2017,

month = apr,

url = {https://magenta.tensorflow.org/sketch-rnn-demo},

}

@ARTICLE{sketchrnndemo,

author = {Ha, D. and Jongejan, J. and Johnson, I.},

title = "Draw Together with a Neural Network",

journal={Google AI Experiments},

year = 2017,

month = jun,

url = {https://magenta.tensorflow.org/sketch-rnn-demo},

}

@article{carter2016experiments,

author = {Carter, Shan and Ha, David and Johnson, Ian and Olah, Chris},

title = {Experiments in Handwriting with a Neural Network},

journal = {Distill},

year = {2016},

url = {http://distill.pub/2016/handwriting},

doi = {10.23915/distill.00004}

}

@ARTICLE{openai_gym,

author = {Brockman, G. and Cheung, V. and Pettersson, L. and Schneider, J. and Schulman, J. and Tang, J. and Zaremba, W.},

title={OpenAI Gym},

journal={ArXiv preprint},

year = 2016,

month = jun,

url = {https://arxiv.org/abs/1606.01540},

}

@ARTICLE{competitive_self_play,

author = {Bansal, T. and Pachocki, J. and Sidor, S. and Sutskever, I. and Mordatch, I.},

journal={ArXiv preprint},

title={Emergent Complexity via Multi-Agent Competition},

year = 2017,

month = oct,

url = {https://arxiv.org/abs/1710.03748},

}

@ARTICLE{continuous_adaptation_via_meta_learning,

author = {Al-Shedivat, M. and Bansal, T. and Burda, Y. and Sutskever, I. and Mordatch, I. and Abbeel, P.},

journal={ArXiv preprint},

title={Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments},

year = 2017,

month = oct,

url = {https://arxiv.org/abs/1710.03641},

}

@ARTICLE{asymmetric_self_play,

author = {Sukhbaatar, S. and Lin, Z. and Kostrikov, I. and Synnaeve, G. and Szlam, A. and Fergus, R.},

journal={ArXiv preprint},

title={Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play},

year = 2017,

month = oct,

url = {https://arxiv.org/abs/1703.05407},

}

@article{brain_capacity,

author = {Bartol, Thomas M, Jr and Bromer, Cailey and Kinney, Justin and Chirillo, Michael A and Bourne, Jennifer N and Harris, Kristen M and Sejnowski, Terrence J},

title = {Nanoconnectomic upper bound on the variability of synaptic plasticity},

journal = {eLife Sciences Publications, Ltd},

year = {2015},

doi = {10.7554/eLife.10778},

url = {https://doi.org/10.7554/eLife.10778}

}

@ARTICLE{outrageously_large_neural_nets,

author = {Shazeer, N. and Mirhoseini, A. and Maziarz, K. and Davis, A. and Le, Q. and Hinton, G. and Dean, J.},

journal={ArXiv preprint},

title={Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer},

year = 2017,

month = jan,

url = {https://arxiv.org/abs/1701.06538},

}

@ARTICLE{hypernetworks,

author = "Ha, D. and Dai, A. and Le, Q.",

journal={ArXiv preprint},

title="HyperNetworks",

year = 2016,

month = sep,

url = {https://arxiv.org/abs/1609.09106},

}

@incollection{suarez2017,

title = {Language Modeling with Recurrent Highway Hypernetworks},

author = {Suarez, Joseph},

booktitle = {Advances in Neural Information Processing Systems 30},

editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},

pages = {3269--3278},

year = {2017},

publisher = {Curran Associates, Inc.},

url = {http://papers.nips.cc/paper/6919-language-modeling-with-recurrent-highway-hypernetworks.pdf}

}

@article{lstm,

title={Long short-term memory},

author={Hochreiter, Sepp and Schmidhuber, Juergen},

journal={Neural Computation},

year={1997},

publisher={MIT Press},

url={ftp://ftp.idsia.ch/pub/juergen/lstm.pdf}

}

@ARTICLE{Kirkpatrick2016,

author = {Kirkpatrick, J. and Pascanu, R. and Rabinowitz, N. and Veness, J. and Desjardins, G. and Rusu, A.and Milan, K. and Quan, J. and Ramalho, T. and Grabska-Barwinska, A. and Hassabis, D. and Clopath, C. and Kumaran, D. and Hadsell, R.},

title = "Overcoming catastrophic forgetting in neural networks",

journal={ArXiv preprint},

year = 2016,

month = dec,

url = {https://arxiv.org/abs/1612.00796}

}

@article{Ratcliff1990,

title={Connectionist models of recognition memory: constraints imposed by learning and forgetting functions.},

author={Rodney Mark Ratcliff},

journal={Psychological review},

year={1990},

volume={97 2},

pages={285-308}

}

@incollection{French1994,

title = {Catastrophic interference in connectionist networks: Can It Be predicted, can It be prevented?},

author = {Robert M. French},

booktitle = {Advances in Neural Information Processing Systems 6},

editor = {J. D. Cowan and G. Tesauro and J. Alspector},

pages = {1176--1177},

year = {1994},

publisher = {Morgan-Kaufmann},

url = {http://papers.nips.cc/paper/799-catastrophic-interference-in-connectionist-networks-can-it-be-predicted-can-it-be-prevented.pdf}

}

@online{graves_lecture,

author = {Alex Graves},

title = {Hallucination with Recurrent Neural Networks},

year = 2015,

url = {https://www.youtube.com/watch?v=-yX1SYeDHbg&t=49m33s},

urldate = {2017-11-01}

}

@online{dyna_slides,

author = {David Silver},

title = "David Silver's Lecture on Integrating Learning and Planning",

year = 2017,

url = {http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/dyna.pdf},

urldate = {2017-12-13}

}

@online{fastball_video,

author = {Josh Salwen},

title = "2015 MLB Home Run Swings",

publisher = "YouTube, Creative Commons License.",

year = 2016,

url = {https://youtu.be/FlHRHrt6fkk},

urldate = {2017-11-01}

}

@online{finn_lecture,

author = {Chelsea Finn},

title = {Model-Based RL Lecture at Deep RL Bootcamp 2017},

year = 2017,

url = {https://youtu.be/iC2a7M9voYU?t=44m35s},

urldate = {2017-11-01}

}

@inproceedings{game_engine_learning,

author = {Matthew Guzdial, Boyang Li, Mark O. Riedl},

title = {Game Engine Learning from Video},

booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on

Artificial Intelligence, IJCAI-17},

pages = {3707--3713},

year = {2017},

doi = {10.24963/ijcai.2017/518},

url = {https://doi.org/10.24963/ijcai.2017/518},

}

@ARTICLE{learn_to_act_by_predicting_future,

author = {Dosovitskiy, A. and Koltun, V.},

title = "Learning to Act by Predicting the Future",

journal={ArXiv preprint},

year = 2016,

month = nov,

url = {https://arxiv.org/abs/1611.01779},

}

@ARTICLE{learning_multimodal_dynamics,

author = {Moerland, T. and Broekens, J. and Jonker, C.},

title = "Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning",

journal={ArXiv preprint},

year = 2017,

month = may,

url = {https://arxiv.org/abs/1705.00470},

}

@ARTICLE{learning_deep_dynamical_models_from_image_pixels,

author = {Wahlström, N. and Schön, T. and Deisenroth, M.},

title = "Learning deep dynamical models from image pixels",

journal={ArXiv preprint},

year = 2014,

month = oct,

url = {https://arxiv.org/abs/1410.7550},

}

@ARTICLE{from_pixels_to_torques,

author = {Wahlström, N. and Schön, T. and Deisenroth, M.},

title = "From Pixels to Torques: Policy Learning with Deep Dynamical Models",

journal={ArXiv preprint},

year = 2015,

month = jun,

url = {https://arxiv.org/abs/1502.02251},

}

@ARTICLE{embed_to_control,

author = {Watter, M. and Springenberg, J. and Boedecker, J. and Riedmiller, M.},

title = "Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images",

journal={ArXiv preprint},

year = 2015,

month = jun,

url = "https://arxiv.org/abs/1506.07365",

}

@ARTICLE{deep_spacial_autoencoders,

author = {Finn, C. and Tan, X. and Duan, Y. and Darrell, T. and Levine, S. and Abbeel, P.},

title = "Deep Spatial Autoencoders for Visuomotor Learning",

journal={ArXiv preprint},

year = 2015,

month = sep,

url = {https://arxiv.org/abs/1509.06113},

}

@ARTICLE{action_conditional_video_prediction,

author = {Oh, J. and Guo, X. and Lee, H. and Lewis, R. and Singh, S.},

title = "Action-Conditional Video Prediction using Deep Networks in Atari Games",

journal={ArXiv preprint},

year = 2015,

month = jul,

url = {https://arxiv.org/abs/1507.08750}

}

@ARTICLE{imagination_agent,

author = {Weber, T. and Racanière, S. and Reichert, D. and Buesing, L. and Guez, A. and Rezende, D. and Badia, A. and Vinyals, O. and Heess, N. and Li, Y. and Pascanu, R. and Battaglia, P. and Silver, D. and Wierstra, D.},

title = "Imagination-Augmented Agents for Deep Reinforcement Learning",

journal={ArXiv preprint},

year = 2017,

month = jul,

url = {https://arxiv.org/abs/1707.06203}

}

@article{intrinsic_motivation,

author = "Oudeyer, P. and Kaplan, F. and Hafner, V.",

title = "Intrinsic Motivation Systems for Autonomous Mental Development",

journal = "Trans. Evol. Comp",

year = 2007,

month = "apr",

url = "http://www.pyoudeyer.com/ims.pdf",

doi = "10.1109/TEVC.2006.890271",

publisher = "IEEE Press",

}

@article{schmidhuber_creativity,

author = "Schmidhuber, J.",

journal = "IEEE Trans. Autonomous Mental Development",

title = "Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990-2010).",

url = "http://people.idsia.ch/~juergen/creativity.html",

year = 2010,

}

@ARTICLE{dqn,

author = {Mnih, V. and Kavukcuoglu, K. and Silver, D. and Graves, A. and Antonoglou, I. and Wierstra, D. and Riedmiller, M.},

title = "Playing Atari with Deep Reinforcement Learning",

journal={ArXiv preprint},

year = 2013,

month = dec,

url = {https://arxiv.org/abs/1312.5602},

}

@article{hausknecht,

title={A Neuroevolution Approach to General Atari Game Playing},

author={Hausknecht, M. and Lehman, J. and Miikkulainen, R. and Stone, P.},

journal={IEEE Transactions on Computational Intelligence and AI in Games},

url="http://www.cs.utexas.edu/~ai-lab/?atari",

year={2013}

}

@ARTICLE{pathnet,

author = {Fernando, C. and Banarse, D. and Blundell, C. and Zwols, Y. and Ha, D. and Rusu, A. and Pritzel, A. and Wierstra, D.},

title = "PathNet: Evolution Channels Gradient Descent in Super Neural Networks",

journal={ArXiv preprint},

year = 2017,

month = jan,

url = {https://arxiv.org/abs/1701.08734},

}

@article{hyperneat,

author = {Gauci, Jason and Stanley, Kenneth O.},

title = {Autonomous Evolution of Topographic Regularities in Artificial Neural Networks},

journal = {Neural Computation},

issue_date = {July 2010},

volume = {22},

number = {7},

month = jul,

year = {2010},

issn = {0899-7667},

pages = {1860--1898},

numpages = {39},

url = {http://eplex.cs.ucf.edu/papers/gauci_nc10.pdf},

doi = {10.1162/neco.2010.06-09-1042},

acmid = {1810223},

publisher = {MIT Press},

address = {Cambridge, MA, USA},

@Article{neat,

title={Evolving Neural Networks Through Augmenting Topologies},

author={Kenneth O. Stanley and Risto Miikkulainen},

volume={10},

journal={Evolutionary Computation},

number={2},

pages={99-127},

year={2002}

@article{pepg,

author = {Sehnke, F. and Osendorfer, C. and Ruckstieb, T. and Graves, A. and Peters, J. and Schmidhuber, J.},

title = {Parameter-exploring policy gradients},

journal = {Neural Networks},

volume = {23},

number = {4},

pages = {551--559},

year = {2010},

url = "http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=A64D1AE8313A364B814998E9E245B40A?doi=10.1.1.180.7104&rep=rep1&type=pdf",

doi = {10.1016/j.neunet.2009.12.004},

@article{parker2012,

title={Neuro-Visual Control in the Quake II Environment},

author={Parker, M. and Bryant, B.},

journal={IEEE Transactions on Computational Intelligence and AI in Games},

url="https://www.cse.unr.edu/~bdbryant/papers/parker-2012-tciaig.pdf",

year={2012}

}

@article{evolving_neural_networks,

title={Evolving Neural Networks},

author={Miikkulainen, R.},

journal={IJCNN},

year=2013,

month=aug,

url={http://nn.cs.utexas.edu/downloads/slides/miikkulainen.ijcnn13.pdf},

}

@ARTICLE{vae_evolution,

author = {Alvernaz, S. and Togelius, J.},

title = "Autoencoder-augmented Neuroevolution for Visual Doom Playing",

journal = {ArXiv preprint},

primaryClass = "cs.AI",

keywords = {Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing},

year = 2017,

month = jul,

url = {https://arxiv.org/abs/1707.03902},

@ARTICLE{recurrent_env_sim,

author = {Chiappa, S. and Racaniere, S. and Wierstra, D. and Mohamed, S.},

title = "Recurrent Environment Simulators",

journal = {ArXiv preprint},

primaryClass = "cs.AI",

keywords = {Computer Science - Artificial Intelligence, Computer Science - Learning, Statistics - Machine Learning},

year = 2017,

month = apr,

url = {https://arxiv.org/abs/1704.02254},

@book{Rechenberg1973,

author = {Rechenberg, I.},

keywords = {neurofitter},

posted-at = {2007-10-03 02:05:07},

priority = {2},

publisher = {Frommann-Holzboog},

title = {Evolutionsstrategie: optimierung technischer systeme nach prinzipien der biologischen evolution},

year = {1973},

url = {https://en.wikipedia.org/wiki/Ingo_Rechenberg}

@book{Schwefel1977,

author = {Schwefel, H.},

title = {Numerical Optimization of Computer Models},

year = {1977},

isbn = {0471099880},

publisher = {John Wiley and Sons, Inc.},

address = {New York, NY, USA},

url = {https://en.wikipedia.org/wiki/Hans-Paul_Schwefel}

@article{s03_overview,

author = "J. Schmidhuber",

title = "Deep Learning in Neural Networks: An Overview",

journal = "Neural Networks",

pages = "85-117",

volume = "61",

doi = "10.1016/j.neunet.2014.09.003",

note = "Published online 2014; based on TR arXiv:1404.7828 [cs.NE]",

year = "2015"

@article{s04_trajectories,

author = {Schmidhuber, J. and Huber, R},

title = {Learning to Generate Artificial Fovea Trajectories for Target Detection},

journal = {International Journal of Neural Systems},

volume = {2},

number = {1-2},

pages = {125--134},

year = {1991},

url = {ftp://ftp.idsia.ch/pub/juergen/attention.pdf},

doi = {10.1142/S012906579100011X},

@article{s05a_cm,

author={J. Schmidhuber},

journal={1990 IJCNN International Joint Conference on Neural Networks},

title={An on-line algorithm for dynamic reinforcement learning and planning in reactive environments},

year={1990},

pages={253-258 vol.2},

doi={10.1109/IJCNN.1990.137723},

month={June},

url="ftp://ftp.idsia.ch/pub/juergen/ijcnn90.ps.gz",

@article{s05b_rl,

title = {Reinforcement Learning in Markovian and Non-Markovian Environments},

author = {Schmidhuber, J.},

journal = {Advances in Neural Information Processing Systems 3},

editor = {R. P. Lippmann and J. E. Moody and D. S. Touretzky},

pages = {500--506},

year = {1991},

publisher = {Morgan-Kaufmann},

url = {http://papers.nips.cc/paper/393-reinforcement-learning-in-markovian-and-non-markovian-environments.pdf}

@article{s05c_boredom,

author = {Schmidhuber, J.},

title = {A Possibility for Implementing Curiosity and Boredom in Model-building Neural Controllers},

journal = {Proceedings of the First International Conference on Simulation of Adaptive Behavior on From Animals to Animats},

year = {1990},

isbn = {0-262-63138-5},

location = {Paris, France},

pages = {222--227},

numpages = {6},

url = {ftp://ftp.idsia.ch/pub/juergen/curiositysab.pdf},

acmid = {116542},

publisher = {MIT Press},

address = {Cambridge, MA, USA},

@article{s05_making_the_world_differentiable,

author = {J. Schmidhuber},

title = {Making the World Differentiable: On Using Self-Supervised Fully Recurrent Neural Networks for Dynamic Reinforcement Learning and Planning in Non-Stationary Environments},

url = {http://people.idsia.ch/~juergen/FKI-126-90_(revised)bw_ocr.pdf},

year = {1990}

@article{gom5_ne_accelerated,

author = {Gomez, F. and Schmidhuber, J. and Miikkulainen, R.},

title = {Accelerated Neural Evolution Through Cooperatively Coevolved Synapses},

journal = {Journal of Machine Learning Research},

issue_date = {6/1/2008},

volume = {9},

month = jun,

year = {2008},

issn = {1532-4435},

pages = {937--965},

numpages = {29},

url = {http://people.idsia.ch/~juergen/gomez08a.pdf},

acmid = {1390712},

publisher = {JMLR.org},

@article{gom2_coevolve,

author = {Gomez, F. and Schmidhuber, J.},

title = {Co-evolving Recurrent Neurons Learn Deep Memory POMDPs},

journal = {Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation},

series = {GECCO 2005},

year = {2005},

isbn = {1-59593-010-8},

location = {Washington DC, USA},

pages = {491--498},

numpages = {8},

url = {ftp://ftp.idsia.ch/pub/juergen/gecco05gomez.pdf},

doi = {10.1145/1068009.1068092},

acmid = {1068092},

publisher = {ACM},

address = {New York, NY, USA},

keywords = {POMDP, coevolution, recurrent neural networks},

@article{kou1_torcs,

author = {Koutnik, J. and Cuccu, G. and Schmidhuber, J. and Gomez, F.},

title = {Evolving Large-scale Neural Networks for Vision-based Reinforcement Learning},