{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:46:40Z","timestamp":1775130400629,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3008735","type":"journal-article","created":{"date-parts":[[2020,7,13]],"date-time":"2020-07-13T21:54:01Z","timestamp":1594677241000},"page":"128809-128818","source":"Crossref","is-referenced-by-count":22,"title":["Efficient Novelty Search Through Deep Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4334-1182","authenticated-orcid":false,"given":"Longxiang","family":"Shi","sequence":"first","affiliation":[]},{"given":"Shijian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Min","family":"Yao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4049-6181","authenticated-orcid":false,"given":"Gang","family":"Pan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref32","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref34","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref10","article-title":"Illuminating search spaces by mapping elites","author":"mouret","year":"2015","journal-title":"arxiv 1504 04909"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2704781"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754736"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463393"},{"key":"ref14","first-page":"1188","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2576768.2598225"},{"key":"ref16","article-title":"From exploration to control: Learning object manipulation skills through novelty search and local adaptation","author":"kim","year":"2019","journal-title":"arXiv 1901 00811"},{"key":"ref17","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001708"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref28","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref27","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"2753","article-title":"# Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"ref29","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001606"},{"key":"ref7","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"such","year":"2017","journal-title":"arXiv 1712 06567"},{"key":"ref2","first-page":"5027","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","author":"conti","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref1","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"ref22","first-page":"1039","article-title":"GEP-PG: Decoupling exploration and exploitation in deep reinforcement learning algorithms","author":"colas","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1059712310379923"},{"key":"ref24","first-page":"4264","article-title":"Guided evolutionary strategies: Augmenting random search with surrogate gradients","author":"maheswaranathan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref26","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref25","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2018","journal-title":"arXiv 1810 01222"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09139203.pdf?arnumber=9139203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:54:24Z","timestamp":1639770864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9139203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3008735","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}