{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:30:17Z","timestamp":1792600217244,"version":"4.5.0"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007028","name":"Leona M and Harry B Helmsley Charitable Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1627\/17"],"award-info":[{"award-number":["1627\/17"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1016\/j.neunet.2021.10.011","type":"journal-article","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T21:17:39Z","timestamp":1634851059000},"page":"260-270","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":29,"special_numbering":"C","title":["Curriculum learning with Hindsight Experience Replay for sequential object manipulation tasks"],"prefix":"10.1016","volume":"145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1913-2356","authenticated-orcid":false,"given":"B.","family":"Manela","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0087-3675","authenticated-orcid":false,"given":"A.","family":"Biess","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2021.10.011_b1","series-title":"Learning dexterous in-hand manipulation","author":"Andrychowicz","year":"2018"},{"key":"10.1016\/j.neunet.2021.10.011_b2","series-title":"Advances in neural information processing systems","first-page":"5048","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017"},{"key":"10.1016\/j.neunet.2021.10.011_b3","series-title":"Proceedings of the 26th annual international conference on machine learning","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"10.1016\/j.neunet.2021.10.011_b4","series-title":"PlanGAN: Model-based planning with sparse rewards and multiple goals","author":"Charlesworth","year":"2020"},{"key":"10.1016\/j.neunet.2021.10.011_b5","series-title":"Advances in neural information processing systems","first-page":"12623","article-title":"Curriculum-guided hindsight experience replay","author":"Fang","year":"2019"},{"key":"10.1016\/j.neunet.2021.10.011_b6","series-title":"Reverse curriculum generation for reinforcement learning","author":"Florensa","year":"2017"},{"key":"10.1016\/j.neunet.2021.10.011_b7","series-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"10.1016\/j.neunet.2021.10.011_b8","series-title":"Automatic goal generation for reinforcement learning agents","author":"Held","year":"2018"},{"issue":"11","key":"10.1016\/j.neunet.2021.10.011_b9","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","article-title":"Reinforcement learning in robotics: A survey","volume":"32","author":"Kober","year":"2013","journal-title":"International Journal of Robotics Research"},{"key":"10.1016\/j.neunet.2021.10.011_b10","series-title":"AAAI","first-page":"99","article-title":"Complexity analysis of real-time reinforcement learning","author":"Koenig","year":"1993"},{"key":"10.1016\/j.neunet.2021.10.011_b11","series-title":"Reinforcement learning","first-page":"143","article-title":"Transfer in reinforcement learning: a framework and a survey","author":"Lazaric","year":"2012"},{"key":"10.1016\/j.neunet.2021.10.011_b12","series-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017"},{"key":"10.1016\/j.neunet.2021.10.011_b13","series-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"10.1016\/j.neunet.2021.10.011_b14","series-title":"Deep reinforcement learning for complex manipulation tasks with sparse feedback","author":"Manela","year":"2020"},{"key":"10.1016\/j.neunet.2021.10.011_b15","series-title":"Bias-reduced hindsight experience replay with virtual goal prioritization","author":"Manela","year":"2019"},{"key":"10.1016\/j.neunet.2021.10.011_b16","series-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"10.1016\/j.neunet.2021.10.011_b17","series-title":"IJCAI","first-page":"5195","article-title":"Curriculum learning in reinforcement learning","author":"Narvekar","year":"2017"},{"issue":"181","key":"10.1016\/j.neunet.2021.10.011_b18","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2021.10.011_b19","doi-asserted-by":"crossref","unstructured":"Narvekar, Sanmit, Sinapov, Jivko, Leonetti, Matteo, & Stone, Peter (2016). Source task creation for curriculum learning. In Proceedings of the 2016 international conference on autonomous agents & multiagent systems (pp. 566\u2013574).","DOI":"10.65109\/WWRD6174"},{"key":"10.1016\/j.neunet.2021.10.011_b20","series-title":"IJCAI","first-page":"2536","article-title":"Autonomous task sequencing for customized curriculum design in reinforcement learning","author":"Narvekar","year":"2017"},{"key":"10.1016\/j.neunet.2021.10.011_b21","series-title":"Proceedings of the 18th international conference on autonomous agents and multiagent systems","doi-asserted-by":"crossref","first-page":"25","DOI":"10.65109\/UOAZ3967","article-title":"Learning curriculum policies for reinforcement learning","author":"Narvekar","year":"2019"},{"key":"10.1016\/j.neunet.2021.10.011_b22","series-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"Popov","year":"2017"},{"issue":"6","key":"10.1016\/j.neunet.2021.10.011_b23","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1109\/TNNLS.2018.2790981","article-title":"Self-paced prioritized curriculum learning with coverage penalty in deep reinforcement learning","volume":"29","author":"Ren","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2021.10.011_b24","doi-asserted-by":"crossref","unstructured":"Saito, Atsushi (2018). Curriculum learning based on reward sparseness for deep reinforcement learning of task completion dialogue management. In Proceedings of the 2018 EMNLP workshop SCAI: The 2nd international workshop on search-oriented conversational AI (pp. 46\u201351).","DOI":"10.18653\/v1\/W18-5707"},{"key":"10.1016\/j.neunet.2021.10.011_b25","series-title":"Learning Montezuma\u2019s revenge from a single demonstration","author":"Salimans","year":"2018"},{"key":"10.1016\/j.neunet.2021.10.011_b26","series-title":"International conference on machine learning","first-page":"1312","article-title":"Universal value function approximators","author":"Schaul","year":"2015"},{"key":"10.1016\/j.neunet.2021.10.011_b27","series-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"10.1016\/j.neunet.2021.10.011_b28","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"issue":"6419","key":"10.1016\/j.neunet.2021.10.011_b29","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1126\/science.aar6404","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play","volume":"362","author":"Silver","year":"2018","journal-title":"Science"},{"key":"10.1016\/j.neunet.2021.10.011_b30","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"issue":"7","key":"10.1016\/j.neunet.2021.10.011_b31","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2021.10.011_b32","series-title":"2012 IEEE\/RSJ international conference on intelligent robots and systems","first-page":"5026","article-title":"Mujoco: A physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.neunet.2021.10.011_b33","series-title":"AAAI","first-page":"607","article-title":"A complexity analysis of cooperative mechanisms in reinforcement learning","author":"Whitehead","year":"1991"},{"key":"10.1016\/j.neunet.2021.10.011_b34","series-title":"Maximum entropy-regularized multi-goal reinforcement learning","author":"Zhao","year":"2019"},{"key":"10.1016\/j.neunet.2021.10.011_b35","series-title":"Energy-based hindsight experience prioritization","author":"Zhao","year":"2018"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608021004020?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608021004020?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:00:55Z","timestamp":1777579255000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608021004020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":35,"alternative-id":["S0893608021004020"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2021.10.011","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2022,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Curriculum learning with Hindsight Experience Replay for sequential object manipulation tasks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2021.10.011","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}