{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T12:06:49Z","timestamp":1778587609998,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560897","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"10808-10814","source":"Crossref","is-referenced-by-count":6,"title":["Reward Conditioned Neural Movement Primitives for Population-Based Variational Policy Optimization"],"prefix":"10.1109","author":[{"given":"M. Tuluhan","family":"Akbulut","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Utku","family":"Bozdogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmet","family":"Tekden","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emre","family":"Ugur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Proximal distilled evolutionary reinforcement learning","author":"bodnar","year":"2019"},{"key":"ref38","first-page":"1188","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"1747","article-title":"Genetic-gated networks for deep reinforcement learning","author":"chang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"such","year":"2017"},{"key":"ref31","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00089"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1770-5_3"},{"key":"ref36","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":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Instance weighted incremental evolution strategies for reinforcement learning in dynamic environments","author":"wang","year":"2020"},{"key":"ref34","article-title":"Policy optimization by genetic distillation","author":"gangwani","year":"2017"},{"key":"ref10","article-title":"Training agents using upside-down reinforcement learning","author":"srivastava","year":"2019"},{"key":"ref40","article-title":"Cem-rl: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2018"},{"key":"ref11","article-title":"Neural processes","author":"garnelo","year":"2018"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/2889.001.0001","author":"nolfi","year":"2000","journal-title":"Evolutionary Robotics The Biology Intelligence and Technology of Self-Organizing Machines"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.071"},{"key":"ref15","article-title":"Acnmp: Skill transfer and task extrapolation through learning from demonstration and reinforcement learning via representation sharing","author":"akbulut","year":"2020","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","volume":"10","author":"peters","year":"2010","journal-title":"Twenty-Fourth AAAI Conference on Artificial Intelligence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2679202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-015-0187-9"},{"key":"ref28","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref4","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019"},{"key":"ref27","article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","author":"karl","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794074"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968545"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref8","first-page":"9780470544785","article-title":"Reinforcement learning and its relationship to supervised learning","volume":"10","author":"barto","year":"2004","journal-title":"Handbook of Learning and Approximate Dynamic Programming"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","article-title":"Reinforcement learning upside down: Don’t predict rewards – just map them to actions","author":"schmidhuber","year":"2020"},{"key":"ref1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","author":"kroemer","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593450"},{"key":"ref22","first-page":"2616","article-title":"Probabilistic movement primitives","author":"paraschos","year":"2013","journal-title":"NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/S026357471900078X"},{"key":"ref42","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803340"},{"key":"ref41","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref23","first-page":"1704","article-title":"Conditional neural processes","author":"garnelo","year":"2018","journal-title":"ICML"},{"key":"ref44","article-title":"Tutorial on variational autoencoders","author":"doersch","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00324-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836233"},{"key":"ref25","first-page":"933","article-title":"Task-conditioned variational autoencoders for learning movement primitives","author":"noseworthy","year":"2020","journal-title":"Proceedings of the Conference on Robot Learning ser Proceedings of Machine Learning Research"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560897.pdf?arnumber=9560897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:16:56Z","timestamp":1725949016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560897","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}