{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:53:04Z","timestamp":1774353184980,"version":"3.50.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010664","name":"H2020 Future and Emerging Technologies","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. Ind. Electron."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tie.2022.3172754","type":"journal-article","created":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T20:01:02Z","timestamp":1652299262000},"page":"2759-2769","source":"Crossref","is-referenced-by-count":40,"title":["Solving Robotic Manipulation With Sparse Reward Reinforcement Learning Via Graph-Based Diversity and Proximity"],"prefix":"10.1109","volume":"70","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3665-9822","authenticated-orcid":false,"given":"Hongkuan","family":"Zhou","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\/0000-0003-0185-7420","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\/0000-0003-0359-7810","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of 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":"ref10","article-title":"Exploration via hindsight goal generation","volume":"32","author":"ren","year":"0","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088947"},{"key":"ref12","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","first-page":"13022","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","author":"zhao","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref14","first-page":"113","article-title":"Energy-based hindsight experience prioritization","author":"zhao","year":"0","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440280"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref17","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","author":"forestier","year":"2017"},{"key":"ref18","article-title":"Unsupervised learning of goal spaces for intrinsically motivated goal exploration","author":"p\u00e9r\u00e9","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref19","first-page":"1331","article-title":"CURIOUS: Intrinsically motivated modular multi-goal reinforcement learning","author":"colas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3094901"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3044808"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3087796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121403"},{"key":"ref8","article-title":"Curriculum-guided hindsight experience replay","volume":"32","author":"fang","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref7","first-page":"14783","article-title":"Rewriting history with inverse RL: Hindsight inference for policy improvement","volume":"33","author":"eysenbach","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3038072"},{"key":"ref9","first-page":"5049","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref20","article-title":"A survey on intrinsic motivation in reinforcement learning","author":"aubret","year":"2019"},{"key":"ref22","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref21","first-page":"1","article-title":"Recall traces: Backtracking models for efficient reinforcement learning","author":"goyal","year":"0","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref24","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref23","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"0","journal-title":"Proc 1st Conf Robot Learn"},{"key":"ref26","article-title":"Policy continuation with hindsight inverse dynamics","author":"sun","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850721"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/9955034\/09772990.pdf?arnumber=9772990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:26:47Z","timestamp":1670873207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9772990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":27,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tie.2022.3172754","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}