{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:36:57Z","timestamp":1783114617699,"version":"3.54.6"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Bundesministerium f?r Wirtschaft und Klimaschutz (BMWK) of Germany","award":["01ME20002C"],"award-info":[{"award-number":["01ME20002C"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3382264","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T19:28:54Z","timestamp":1711567734000},"page":"46626-46635","source":"Crossref","is-referenced-by-count":8,"title":["Curriculum Learning for Robot Manipulation Tasks With Sparse Reward Through Environment Shifts"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5944-7291","authenticated-orcid":false,"given":"Erdi","family":"Sayar","sequence":"first","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-1830","authenticated-orcid":false,"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"issue":"7540","key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref5","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"arXiv:1801.01290"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"118776","DOI":"10.1109\/ACCESS.2019.2936863","article-title":"Rewards prediction-based credit assignment for reinforcement learning with sparse binary rewards","volume":"7","author":"Seo","year":"2019","journal-title":"IEEE Access"},{"key":"ref8","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"arXiv:1707.01495"},{"key":"ref9","article-title":"Exploration via hindsight goal generation","author":"Ren","year":"2019","journal-title":"arXiv:1906.04279"},{"key":"ref10","first-page":"1","article-title":"Curriculum-guided hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Fang"},{"issue":"12","key":"ref11","doi-asserted-by":"crossref","first-page":"7863","DOI":"10.1109\/TNNLS.2021.3088947","article-title":"Complex robotic manipulation via graph-based hindsight goal generation","volume":"33","author":"Bing","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124366"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071186"},{"key":"ref14","article-title":"Paired open-ended trailblazer (POET): Endlessly generating increasingly complex and diverse learning environments and their solutions","author":"Wang","year":"2019","journal-title":"arXiv:1901.01753"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321723"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2908961.2931675"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659978"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3377929.3389976"},{"issue":"2","key":"ref19","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1162\/106365602320169811","article-title":"Evolving neural networks through augmenting topologies","volume":"10","author":"Stanley","year":"2002","journal-title":"Evol. Comput."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43505-2_44"},{"key":"ref21","article-title":"Natural evolution strategies","author":"Wierstra","year":"2011","journal-title":"arXiv:1106.4487"},{"key":"ref22","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref23","article-title":"Comparing deep reinforcement learning and evolutionary methods in continuous control","author":"Zhang","year":"2017","journal-title":"arXiv:1712.00006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3172754"},{"key":"ref25","article-title":"MHER: Model-based hindsight experience replay","author":"Yang","year":"2021","journal-title":"arXiv:2107.00306"},{"key":"ref26","first-page":"7750","article-title":"Maximum entropy gain exploration for long horizon multi-goal reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pitis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/artl_a_00301"},{"key":"ref28","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv:1802.09464"},{"key":"ref29","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schaul"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81283-5_8"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref32","first-page":"113","article-title":"Energy-based hindsight experience prioritization","volume-title":"Proc. Conf. Robot Learn.","author":"Zhao"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10480429.pdf?arnumber=10480429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T17:51:37Z","timestamp":1712166697000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3382264","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}