{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:54:05Z","timestamp":1781837645904,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,7,13]],"date-time":"2019-07-13T00:00:00Z","timestamp":1562976000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,7,13]]},"DOI":"10.1145\/3321707.3321817","type":"proceedings-article","created":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T13:48:04Z","timestamp":1562161684000},"page":"456-462","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Deep neuroevolution of recurrent and discrete world models"],"prefix":"10.1145","author":[{"given":"Sebastian","family":"Risi","sequence":"first","affiliation":[{"name":"Uber AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth O.","family":"Stanley","sequence":"additional","affiliation":[{"name":"Uber AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080408"},{"key":"e_1_3_2_1_2_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Asai Masataro","year":"2018"},{"key":"e_1_3_2_1_3_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"e_1_3_2_1_5_1","volume-title":"Quantifying generalization in reinforcement learning. arXiv preprint arXiv:1812.02341","author":"Cobbe Karl","year":"2018"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 28th International Conference on machine learning (ICML-11)","author":"Deisenroth Marc","year":"2011"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"e_1_3_2_1_8_1","unstructured":"P. Gerber J. Guan E. Nunez K. Phamdo T. Monsoor and N. Malaya. 2018. Solving OpenAI's Car Racing Environment with Deep Reinforcement Learning and Dropout. https:\/\/github.com\/AMD-RIPS\/RL-2018\/blob\/master\/documents\/nips\/nips_2018.pdf  P. Gerber J. Guan E. Nunez K. Phamdo T. Monsoor and N. Malaya. 2018. Solving OpenAI's Car Racing Environment with Deep Reinforcement Learning and Dropout. https:\/\/github.com\/AMD-RIPS\/RL-2018\/blob\/master\/documents\/nips\/nips_2018.pdf"},{"key":"e_1_3_2_1_9_1","volume-title":"Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850","author":"Graves Alex","year":"2013"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Alex Graves. 2013. Hallucination with recurrent neural networks. https:\/\/www.youtube.com\/watch?v=-yX1SYeDHbg&t=49m33s  Alex Graves. 2013. Hallucination with recurrent neural networks. https:\/\/www.youtube.com\/watch?v=-yX1SYeDHbg&t=49m33s","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Matthew Guzdial Boyang Li and Mark O Riedl. 2017. Game Engine Learning from Video.. In IJCAI. 3707--3713.   Matthew Guzdial Boyang Li and Mark O Riedl. 2017. Game Engine Learning from Video.. In IJCAI. 3707--3713.","DOI":"10.24963\/ijcai.2017\/518"},{"key":"e_1_3_2_1_12_1","volume-title":"A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477","author":"Ha David","year":"2017"},{"key":"e_1_3_2_1_13_1","unstructured":"David Ha and J\u00fcrgen Schmidhuber. 2018. Recurrent world models facilitate policy evolution. In Advances in Neural Information Processing Systems. 2455--2467.   David Ha and J\u00fcrgen Schmidhuber. 2018. Recurrent world models facilitate policy evolution. In Advances in Neural Information Processing Systems. 2455--2467."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_16_1","unstructured":"Min J. Jang S. and C. Lee. 2017. Car racing with A3C. https:\/\/www.scribd.com\/document\/358019044\/  Min J. Jang S. and C. Lee. 2017. Car racing with A3C. https:\/\/www.scribd.com\/document\/358019044\/"},{"key":"e_1_3_2_1_17_1","volume-title":"Deep learning for video game playing. To appear in: IEEE Transactions on Games","author":"Justesen Niels","year":"2019"},{"key":"e_1_3_2_1_18_1","volume-title":"NeurIPS 2018 Workshop on Deep Reinforcement Learning","author":"Justesen Niels","year":"2018"},{"key":"e_1_3_2_1_19_1","unstructured":"M. Khan and O. Elibol. 2018. Car racing using reinforcement learning. https:\/\/web.stanford.edu\/class\/cs221\/2017\/restricted\/p-final\/elibol\/final.pdf.  M. Khan and O. Elibol. 2018. Car racing using reinforcement learning. https:\/\/web.stanford.edu\/class\/cs221\/2017\/restricted\/p-final\/elibol\/final.pdf."},{"key":"e_1_3_2_1_20_1","unstructured":"Oleg Klimov. 2016. Carracing-v0. https:\/\/gym.openai.com\/envs\/CarRacing-v0\/  Oleg Klimov. 2016. Carracing-v0. https:\/\/gym.openai.com\/envs\/CarRacing-v0\/"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2576768.2598358"},{"key":"e_1_3_2_1_22_1","volume-title":"Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients. arXiv preprint arXiv:1712.06563","author":"Lehman Joel","year":"2017"},{"key":"e_1_3_2_1_23_1","unstructured":"Joel Lehman and Kenneth O Stanley. 2008. Exploiting open-endedness to solve problems through the search for novelty.. In ALIFE. 329--336.  Joel Lehman and Kenneth O Stanley. 2008. Exploiting open-endedness to solve problems through the search for novelty.. In ALIFE. 329--336."},{"key":"e_1_3_2_1_24_1","first-page":"2579","article-title":"Visualizing data using t-SNE","author":"van der Maaten Laurens","year":"2008","journal-title":"Journal of machine learning research 9"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Risto Miikkulainen Jason Liang Elliot Meyerson Aditya Rawal Daniel Fink Olivier Francon Bala Raju Hormoz Shahrzad Arshak Navruzyan Nigel Duffy etal 2019. Evolving deep neural networks. In Artificial Intelligence in the Age of Neural Networks and Brain Computing. Elsevier 293--312.  Risto Miikkulainen Jason Liang Elliot Meyerson Aditya Rawal Daniel Fink Olivier Francon Bala Raju Hormoz Shahrzad Arshak Navruzyan Nigel Duffy et al. 2019. Evolving deep neural networks. In Artificial Intelligence in the Age of Neural Networks and Brain Computing. Elsevier 293--312.","DOI":"10.1016\/B978-0-12-815480-9.00015-3"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski etal 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.  Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908812.2908837"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080444"},{"key":"e_1_3_2_1_29_1","unstructured":"Luc. Prieur. 2017. Deep-Q learning for Box2d racecar RL problem. https:\/\/goo.gl\/VpDqSw  Luc. Prieur. 2017. Deep-Q learning for Box2d racecar RL problem. https:\/\/goo.gl\/VpDqSw"},{"key":"e_1_3_2_1_30_1","volume-title":"Techniques for learning binary stochastic feedforward neural networks. arXiv preprint arXiv:1406.2989","author":"Raiko Tapani","year":"2014"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/ARTL_a_00071"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2494596"},{"key":"e_1_3_2_1_33_1","volume-title":"Discrete variational autoencoders. arXiv preprint arXiv:1609.02200","author":"Rolfe Jason Tyler","year":"2016"},{"key":"e_1_3_2_1_34_1","volume-title":"Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864","author":"Salimans Tim","year":"2017"},{"key":"e_1_3_2_1_35_1","volume-title":"An on-line algorithm for dynamic reinforcement learning and planning in reactive environments. In 1990 IJCNN international joint conference on neural networks","author":"Schmidhuber J\u00fcrgen"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. 1889--1897","author":"Schulman John","year":"2015"},{"key":"e_1_3_2_1_37_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_3_2_1_40_1","volume-title":"Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv preprint arXiv:1712.06567","author":"Such Felipe Petroski","year":"2017"},{"key":"e_1_3_2_1_41_1","volume-title":"Yulun Li, Ludwig Schubert, Marc Bellemare, Jeff Clune, and Joel Lehman.","author":"Such Felipe Petroski","year":"2018"},{"key":"e_1_3_2_1_42_1","unstructured":"Corentin Tallec L\u00e9onard Blier and Diviyan Kalainathan. 2018. Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch. https:\/\/github.com\/ctallec\/world-models  Corentin Tallec L\u00e9onard Blier and Diviyan Kalainathan. 2018. Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch. https:\/\/github.com\/ctallec\/world-models"},{"key":"e_1_3_2_1_43_1","unstructured":"Corentin Tallec L\u00e9onard Blier and Diviyan Kalainathan. 2018. Reproducing \"World Models\" Is training the recurrent network really needed ? https:\/\/ctallec.github.io\/world-models\/  Corentin Tallec L\u00e9onard Blier and Diviyan Kalainathan. 2018. Reproducing \"World Models\" Is training the recurrent network really needed ? https:\/\/ctallec.github.io\/world-models\/"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2011.2148116"},{"key":"e_1_3_2_1_45_1","unstructured":"Aaron van den Oord Oriol Vinyals etal 2017. Neural discrete representation learning. In Advances in Neural Information Processing Systems. 6306--6315.   Aaron van den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. In Advances in Neural Information Processing Systems. 6306--6315."},{"key":"e_1_3_2_1_46_1","volume-title":"From pixels to torques: Policy learning with deep dynamical models. arXiv preprint arXiv:1502.02251","author":"Wahlstr\u00f6m Niklas","year":"2015"},{"key":"e_1_3_2_1_47_1","unstructured":"Manuel Watter Jost Springenberg Joschka Boedecker and Martin Riedmiller. 2015. Embed to control: A locally linear latent dynamics model for control from raw images. In Advances in neural information processing systems. 2746--2754.   Manuel Watter Jost Springenberg Joschka Boedecker and Martin Riedmiller. 2015. Embed to control: A locally linear latent dynamics model for control from raw images. In Advances in neural information processing systems. 2746--2754."},{"key":"e_1_3_2_1_48_1","unstructured":"Greg Wayne Chia-Chun Hung David Amos Mehdi Mirza Arun Ahuja Agnieszka Grabska-Barwinska Jack Rae Piotr Mirowski Joel Z Leibo Adam Santoro etal 2018. Unsupervised Predictive Memory in a Goal-Directed Agent. arXiv preprint arXiv:1803.10760 (2018).  Greg Wayne Chia-Chun Hung David Amos Mehdi Mirza Arun Ahuja Agnieszka Grabska-Barwinska Jack Rae Piotr Mirowski Joel Z Leibo Adam Santoro et al. 2018. Unsupervised Predictive Memory in a Goal-Directed Agent. arXiv preprint arXiv:1803.10760 (2018)."},{"key":"e_1_3_2_1_49_1","volume-title":"A study on overfitting in deep reinforcement learning. arXiv preprint arXiv:1804.06893","author":"Zhang Chiyuan","year":"2018"}],"event":{"name":"GECCO '19: Genetic and Evolutionary Computation Conference","location":"Prague Czech Republic","acronym":"GECCO '19","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3321707.3321817","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3321707.3321817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:25:28Z","timestamp":1750206328000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3321707.3321817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,13]]},"references-count":49,"alternative-id":["10.1145\/3321707.3321817","10.1145\/3321707"],"URL":"https:\/\/doi.org\/10.1145\/3321707.3321817","relation":{},"subject":[],"published":{"date-parts":[[2019,7,13]]},"assertion":[{"value":"2019-07-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}