{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:52:02Z","timestamp":1772823122047,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010664","name":"European Union\u2019s Horizon 2020 Framework Programme for Research and Innovation","doi-asserted-by":"publisher","award":["945539"],"award-info":[{"award-number":["945539"]}],"id":[{"id":"10.13039\/100010664","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tnnls.2021.3088947","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:16:38Z","timestamp":1624914998000},"page":"7863-7876","source":"Crossref","is-referenced-by-count":34,"title":["Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0896-2517","authenticated-orcid":false,"given":"Zhenshan","family":"Bing","sequence":"first","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]},{"given":"Matthias","family":"Brucker","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0185-7420","authenticated-orcid":false,"given":"Fabrice O.","family":"Morin","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-8524","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1802-0264","authenticated-orcid":false,"given":"Xiaojie","family":"Su","sequence":"additional","affiliation":[{"name":"School of Automation, Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-7810","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"}]},{"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"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2878977"},{"key":"ref38","article-title":"Policy continuation with hindsight inverse dynamics","volume":"32","author":"sun","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00532240"},{"key":"ref31","first-page":"6910","article-title":"Learning by playing—Solving sparse reward tasks from scratch","volume":"10","author":"riedmiller","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref30","first-page":"1","article-title":"Exploration via hindsight goal generation","author":"ren","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref37","first-page":"1","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref35","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","author":"srinivas","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440280"},{"key":"ref10","first-page":"15220","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","author":"eysenbach","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2849942"},{"key":"ref11","first-page":"1","article-title":"Curriculum-guided hindsight experience replay","author":"fang","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref12","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref13","first-page":"1","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"Proc 1st Conf Robot Learn (CoRL)"},{"key":"ref14","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","author":"forestier","year":"2017","journal-title":"arXiv 1708 02190"},{"key":"ref15","article-title":"Learning actionable representations with goal-conditioned policies","author":"ghosh","year":"2018","journal-title":"arXiv 1811 07819"},{"key":"ref16","first-page":"1","article-title":"Recall traces: Backtracking models for efficient reinforcement learning","author":"goyal","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent (ICLR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2712561"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref19","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref28","first-page":"1","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"arXiv 1802 09464"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref3","article-title":"A survey on intrinsic motivation in reinforcement learning","author":"aubret","year":"2019","journal-title":"arXiv 1908 06976"},{"key":"ref6","first-page":"2372","article-title":"CURIOUS: Intrinsically motivated modular multi-goal reinforcement learning","author":"colas","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref29","first-page":"1","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973099.111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref2","first-page":"419","article-title":"Lipschitz continuity in model-based reinforcement learning","volume":"1","author":"asadi","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850721"},{"key":"ref1","first-page":"5049","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"1","article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","author":"luo","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent (ICLR)"},{"key":"ref45","first-page":"1","article-title":"Curiosity-driven experience prioritization via density estimation","author":"zhao","year":"2019","journal-title":"Proc 32nd Conf Neural Inf Process Syst (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2872043"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790388"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2899588"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2774602"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref44","first-page":"113","article-title":"Energy-based hindsight experience prioritization","author":"zhao","year":"2018","journal-title":"Proc 2nd Conf Robot Learn (CoRL)"},{"key":"ref26","first-page":"1","article-title":"Unsupervised learning of goal spaces for intrinsically motivated goal exploration","author":"p\u00e9r\u00e9","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref43","first-page":"13022","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","author":"zhao","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9966944\/09466373.pdf?arnumber=9466373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:54:24Z","timestamp":1671479664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9466373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":45,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3088947","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}