{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T22:26:00Z","timestamp":1762899960153,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,25]],"date-time":"2020-06-25T00:00:00Z","timestamp":1593043200000},"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":[[2020,6,25]]},"DOI":"10.1145\/3377930.3390217","type":"proceedings-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T19:29:12Z","timestamp":1593458952000},"page":"67-75","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["Scaling MAP-Elites to deep neuroevolution"],"prefix":"10.1145","author":[{"given":"C\u00e9dric","family":"Colas","sequence":"first","affiliation":[{"name":"INRIA"}]},{"given":"Vashisht","family":"Madhavan","sequence":"additional","affiliation":[{"name":"Element Inc."}]},{"given":"Joost","family":"Huizinga","sequence":"additional","affiliation":[{"name":"Uber AI Labs"}]},{"given":"Jeff","family":"Clune","sequence":"additional","affiliation":[{"name":"OpenAI"}]}],"member":"320","published-online":{"date-parts":[[2020,6,26]]},"reference":[{"volume-title":"Surprise-based intrinsic motivation for deep reinforcement learning. arXiv preprint arXiv:1703.01732","year":"2017","author":"Achiam Joshua","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the fourth international conference on genetic algorithms","volume":"2","author":"Back Thomas","year":"1991"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"volume-title":"Intrinsically motivated learning in natural and artificial systems","author":"Barto Andrew G","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","unstructured":"Marc Bellemare Sriram Srinivasan Georg Ostrovski Tom Schaul David Saxton and Remi Munos. 2016. Unifying count-based exploration and intrinsic motivation. In Advances in neural information processing systems. 1471--1479.  Marc Bellemare Sriram Srinivasan Georg Ostrovski Tom Schaul David Saxton and Remi Munos. 2016. Unifying count-based exploration and intrinsic motivation. In Advances in neural information processing systems. 1471--1479."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566979"},{"volume-title":"MULEX: Disentangling Exploitation from Exploration in Deep RL. arXiv preprint arXiv:1907.00868","year":"2019","author":"Beyer Lucas","key":"e_1_3_2_1_7_1"},{"volume-title":"Openai gym. arXiv preprint arXiv:1606.01540","year":"2016","author":"Brockman Greg","key":"e_1_3_2_1_8_1"},{"volume-title":"Exploration by random network distillation. arXiv preprint arXiv:1810.12894","year":"2018","author":"Burda Yuri","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.11.010"},{"volume-title":"Gep-pg: Decoupling exploration and exploitation in deep reinforcement learning algorithms. arXiv preprint arXiv:1802.05054","year":"2018","author":"Colas C\u00e9dric","key":"e_1_3_2_1_11_1"},{"volume-title":"Joel Lehman, Kenneth Stanley, and Jeff Clune.","year":"2018","author":"Conti Edoardo","key":"e_1_3_2_1_12_1"},{"volume-title":"Robots that can adapt like animals. Nature 521, 7553","year":"2015","author":"Cully Antoine","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2704781"},{"volume-title":"Go-explore: a new approach for hard-exploration problems. arXiv preprint arXiv:1901.10995","year":"2019","author":"Ecoffet Adrien","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305498"},{"volume-title":"Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space. arXiv preprint arXiv:1912.02400","year":"2019","author":"Fontaine Matthew C","key":"e_1_3_2_1_17_1"},{"volume-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning. arXiv preprint arXiv:1708.02190","year":"2017","author":"Forestier S\u00e9bastien","key":"e_1_3_2_1_18_1"},{"volume-title":"Meta learning shared hierarchies. arXiv preprint arXiv:1710.09767","year":"2017","author":"Frans Kevin","key":"e_1_3_2_1_19_1"},{"volume-title":"Herke Van Hoof, and David Meger","year":"2018","author":"Fujimoto Scott","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321876"},{"volume-title":"Adversarial policies: Attacking deep reinforcement learning. arXiv preprint arXiv:1905.10615","year":"2019","author":"Gleave Adam","key":"e_1_3_2_1_22_1"},{"volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249--256","year":"2010","author":"Glorot Xavier","key":"e_1_3_2_1_23_1"},{"volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290","year":"2018","author":"Haarnoja Tuomas","key":"e_1_3_2_1_24_1"},{"volume-title":"The CMA evolution strategy: A tutorial. arXiv preprint arXiv:1604.00772","year":"2016","author":"Hansen Nikolaus","key":"e_1_3_2_1_25_1"},{"volume-title":"Filip De Turck, and Pieter Abbeel","year":"2016","author":"Houthooft Rein","key":"e_1_3_2_1_26_1"},{"volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","year":"2014","author":"Kingma Diederik P","key":"e_1_3_2_1_27_1"},{"volume-title":"Map-based multi-policy reinforcement learning: enhancing adaptability of robots by deep reinforcement learning. arXiv preprint arXiv:1710.06117","year":"2017","author":"Kume Ayaka","key":"e_1_3_2_1_28_1"},{"volume-title":"Proceedings of the 7th International Conference on Computational Creativity.","year":"2016","author":"Lehman Joel","key":"e_1_3_2_1_29_1"},{"key":"e_1_3_2_1_30_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_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001606"},{"volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","year":"2015","author":"Lillicrap Timothy P","key":"e_1_3_2_1_32_1"},{"volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","year":"2013","author":"Mnih Volodymyr","key":"e_1_3_2_1_33_1"},{"volume-title":"Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909","year":"2015","author":"Mouret Jean-Baptiste","key":"e_1_3_2_1_34_1"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754703"},{"volume-title":"Gotta learn fast: A new benchmark for generalization in rl. arXiv preprint arXiv:1804.03720","year":"2018","author":"Nichol Alex","key":"e_1_3_2_1_36_1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"volume-title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments. arXiv preprint arXiv:1910.07224","year":"2019","author":"Portelas R\u00e9my","key":"e_1_3_2_1_39_1"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45823-6_82"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754664"},{"volume-title":"Evolutionsstrategie---Optimierung technischer Systeme nach Prinzipien der biologischen Information. Stuttgart-Bad Cannstatt: Friedrich Frommann Verlag","year":"1973","author":"Rechenberg Ingo","key":"e_1_3_2_1_42_1"},{"volume-title":"Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864","year":"2017","author":"Salimans Tim","key":"e_1_3_2_1_43_1"},{"volume-title":"Proc. of the international conference on simulation of adaptive behavior: From animals to animats. 222--227","year":"1991","author":"Schmidhuber J\u00fcrgen","key":"e_1_3_2_1_44_1"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"volume-title":"Model-based active exploration. arXiv preprint arXiv:1810.12162","year":"2018","author":"Shyam Pranav","key":"e_1_3_2_1_46_1"},{"volume-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv preprint arXiv:1712.06567","year":"2017","author":"Such Felipe Petroski","key":"e_1_3_2_1_47_1"},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","key":"e_1_3_2_1_48_1"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2735550"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2008.4631255"},{"volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8, 3-4","year":"1992","author":"Williams Ronald J","key":"e_1_3_2_1_51_1"},{"volume-title":"Scheduled intrinsic drive: A hierarchical take on intrinsically motivated exploration. arXiv preprint arXiv:1903.07400","year":"2019","author":"Zhang Jingwei","key":"e_1_3_2_1_52_1"}],"event":{"name":"GECCO '20: Genetic and Evolutionary Computation Conference","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"location":"Canc\u00fan Mexico","acronym":"GECCO '20"},"container-title":["Proceedings of the 2020 Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377930.3390217","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3377930.3390217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:40:59Z","timestamp":1750200059000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377930.3390217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,25]]},"references-count":52,"alternative-id":["10.1145\/3377930.3390217","10.1145\/3377930"],"URL":"https:\/\/doi.org\/10.1145\/3377930.3390217","relation":{},"subject":[],"published":{"date-parts":[[2020,6,25]]},"assertion":[{"value":"2020-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}