{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:40:42Z","timestamp":1776469242018,"version":"3.51.2"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202306720022"],"award-info":[{"award-number":["202306720022"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306110"],"award-info":[{"award-number":["62306110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372121"],"award-info":[{"award-number":["62372121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2023JJ30411"],"award-info":[{"award-number":["2023JJ30411"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M693976"],"award-info":[{"award-number":["2021M693976"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan Province of China","doi-asserted-by":"publisher","award":["2024AQ2020"],"award-info":[{"award-number":["2024AQ2020"]}],"id":[{"id":"10.13039\/501100019091","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":[[2026,7]]},"DOI":"10.1016\/j.neunet.2026.108769","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:22:21Z","timestamp":1771950141000},"page":"108769","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Framework for hierarchical deep reinforcement learning with conceptual embedding"],"prefix":"10.1016","volume":"199","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5913-8774","authenticated-orcid":false,"given":"Yinglong","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7308-0925","authenticated-orcid":false,"given":"Zhi","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3101-749X","authenticated-orcid":false,"given":"Qiangfu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1494-901X","authenticated-orcid":false,"given":"Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9875-4182","authenticated-orcid":false,"given":"Guojun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108769_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.datak.2023.102240","article-title":"Hierarchical framework for interpretable and specialized deep reinforcement learning-based predictive maintenance","volume":"149","author":"Abbas","year":"2024","journal-title":"Data & Knowledge Engineering"},{"key":"10.1016\/j.neunet.2026.108769_bib0002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.58496\/BJML\/2023\/001","article-title":"A review on machine learning strategies for real-world engineering applications","volume":"2023","author":"Alsajri","year":"2023","journal-title":"Babylonian Journal of Machine Learning"},{"key":"10.1016\/j.neunet.2026.108769_bib0003","series-title":"Proceedings of the thirty-first AAAI conference on artificial intelligence","first-page":"1726","article-title":"The option-critic architecture","author":"Bacon","year":"2017"},{"key":"10.1016\/j.neunet.2026.108769_bib0004","series-title":"AAAI","first-page":"1016","article-title":"Using abstractions for decision-theoretic planning with time constraints","author":"Boutilier","year":"1994"},{"key":"10.1016\/j.neunet.2026.108769_bib0005","series-title":"Advances in neural information processing systems 36, New Orleans, LA, USA","article-title":"Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks","author":"Chevalier-Boisvert","year":"2023"},{"issue":"6","key":"10.1016\/j.neunet.2026.108769_bib0006","doi-asserted-by":"crossref","first-page":"6936","DOI":"10.1007\/s10489-022-03788-7","article-title":"Interpreting a deep reinforcement learning model with conceptual embedding and performance analysis","volume":"53","author":"Dai","year":"2023","journal-title":"Applied Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2026.108769_bib0007","first-page":"1631","article-title":"Conceptual alignment deep neural networks","volume":"34","author":"Dai","year":"2018","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.1016\/j.neunet.2026.108769_bib0008","series-title":"Advances in neural information processing systems 5","first-page":"271","article-title":"Feudal reinforcement learning","author":"Dayan","year":"1992"},{"key":"10.1016\/j.neunet.2026.108769_bib0009","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"Hierarchical reinforcement learning with the MAXQ value function decomposition","volume":"13","author":"Dietterich","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"1","key":"10.1016\/j.neunet.2026.108769_bib0010","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/s42256-021-00433-9","article-title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","volume":"4","author":"Eppe","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108769_bib0011","series-title":"7th international conference on learning representations, ICLR 2019, New Orleans, LA, USA","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2019"},{"issue":"2","key":"10.1016\/j.neunet.2026.108769_bib0012","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1109\/TAI.2025.3584286","article-title":"Hierarchical reinforcement learning for mapless moving target navigation with communication interruption","volume":"7","author":"Feng","year":"2026","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108769_sbref0013","series-title":"The thirty-ninth annual conference on neural information processing systems","article-title":"Self-improving embodied foundation models","author":"Ghasemipour","year":"2025"},{"issue":"4","key":"10.1016\/j.neunet.2026.108769_bib0014","first-page":"4782","article-title":"Information optimization and transferable state abstractions in deep reinforcement learning","volume":"45","author":"Gomez","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"10.1016\/j.neunet.2026.108769_bib0015","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1023\/A:1022693717366","article-title":"A heuristic approach to the discovery of macro-operators","volume":"3","author":"Iba","year":"1989","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.108769_bib0016","first-page":"3885","article-title":"Discrete compositional representations as an abstraction for goal conditioned reinforcement learning","volume":"35","author":"Islam","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108769_bib0017","doi-asserted-by":"crossref","first-page":"3","DOI":"10.58496\/ADSA\/2025\/002","article-title":"Limitations of deep learning vs. human intelligence: Training data, interpretability, bias, and ethics","volume":"2025","author":"Khaleel","year":"2025","journal-title":"Applied Data Science and Analysis"},{"issue":"1","key":"10.1016\/j.neunet.2026.108769_bib0018","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/0004-3702(85)90012-8","article-title":"Macro-operators: A weak method for learning","volume":"26","author":"Korf","year":"1985","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108769_bib0019","series-title":"Proceedings of the 30th international conference on neural information processing systems","first-page":"3682","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"Kulkarni","year":"2016"},{"issue":"1","key":"10.1016\/j.neunet.2026.108769_bib0020","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"issue":"80","key":"10.1016\/j.neunet.2026.108769_bib0021","first-page":"1","article-title":"Temporal abstraction in reinforcement learning with the successor representation","volume":"24","author":"Machado","year":"2023","journal-title":"Journal of Machine Learning Research"},{"issue":"7540","key":"10.1016\/j.neunet.2026.108769_bib0022","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":"10.1016\/j.neunet.2026.108769_bib0023","series-title":"Proceedings of the 32nd international conference on neural information processing systems","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","author":"Nachum","year":"2018"},{"key":"10.1016\/j.neunet.2026.108769_bib0024","series-title":"Advances in neural information processing systems","article-title":"Reinforcement learning with hierarchies of machines","volume":"vol. 10","author":"Parr","year":"1997"},{"issue":"5","key":"10.1016\/j.neunet.2026.108769_bib0025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453160","article-title":"Hierarchical reinforcement learning: A comprehensive survey","volume":"54","author":"Pateria","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.neunet.2026.108769_bib0026","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"9417","article-title":"Scaling marginalized importance sampling to high-dimensional state-spaces via state abstraction","volume":"vol. 37","author":"Pavse","year":"2023"},{"key":"10.1016\/j.neunet.2026.108769_bib0027","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv: 1707.06347."},{"issue":"7676","key":"10.1016\/j.neunet.2026.108769_bib0028","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"Silver","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2026.108769_bib0029","series-title":"Advances in neural information processing systems","article-title":"Reinforcement learning with soft state aggregation","volume":"vol. 7","author":"Singh","year":"1994"},{"issue":"1\u20132","key":"10.1016\/j.neunet.2026.108769_bib0030","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108769_bib0031","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1553","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"Tessler","year":"2017"},{"key":"10.1016\/j.neunet.2026.108769_bib0032","series-title":"Proceedings of the 34th international conference on machine learning","first-page":"3540","article-title":"FeUdal networks for hierarchical reinforcement learning","volume":"vol. 70","author":"Vezhnevets","year":"2017"},{"issue":"7782","key":"10.1016\/j.neunet.2026.108769_bib0033","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"issue":"4","key":"10.1016\/j.neunet.2026.108769_bib0034","doi-asserted-by":"crossref","first-page":"5064","DOI":"10.1109\/TNNLS.2022.3207346","article-title":"Deep reinforcement learning: A survey","volume":"35","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.1016\/j.neunet.2026.108769_bib0035","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1038\/s42256-021-00431-x","article-title":"Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement","volume":"4","author":"Wang","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108769_bib0036","series-title":"Proceedings of the conference on robot learning","first-page":"1146","article-title":"Macro-action-based deep multi-agent reinforcement learning","volume":"vol. 100","author":"Xiao","year":"2020"},{"issue":"6","key":"10.1016\/j.neunet.2026.108769_bib0037","doi-asserted-by":"crossref","first-page":"4747","DOI":"10.1109\/TSG.2022.3181329","article-title":"A hierarchical deep reinforcement learning-based community energy trading scheme for a neighborhood of smart households","volume":"13","author":"Yan","year":"2022","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"9","key":"10.1016\/j.neunet.2026.108769_bib0038","doi-asserted-by":"crossref","first-page":"4727","DOI":"10.1109\/TNNLS.2021.3059912","article-title":"Hierarchical reinforcement learning with universal policies for multistep robotic manipulation","volume":"33","author":"Yang","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.108769_bib0039","doi-asserted-by":"crossref","first-page":"2510","DOI":"10.1109\/TNNLS.2022.3190379","article-title":"Hierarchical deep reinforcement learning-based propofol infusion assistant framework in anesthesia","volume":"35","author":"Yun","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108769_bib0040","doi-asserted-by":"crossref","first-page":"150","DOI":"10.58496\/ADSA\/2023\/014","article-title":"Does lack of knowledge and hardship of information access signify powerful AI? a large language model perspective","volume":"2023","author":"Zahid","year":"2023","journal-title":"Applied Data Science and Analysis"},{"issue":"4","key":"10.1016\/j.neunet.2026.108769_bib0041","doi-asserted-by":"crossref","first-page":"4152","DOI":"10.1109\/TPAMI.2022.3192418","article-title":"Adjacency constraint for efficient hierarchical reinforcement learning","volume":"45","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"10.1016\/j.neunet.2026.108769_bib0042","doi-asserted-by":"crossref","first-page":"4962","DOI":"10.1109\/TIE.2022.3190850","article-title":"A hierarchical deep reinforcement learning framework with high efficiency and generalization for fast and safe navigation","volume":"70","author":"Zhu","year":"2023","journal-title":"IEEE Transactions on Industrial Electronics"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002315?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026002315?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T22:46:17Z","timestamp":1776465977000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026002315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":42,"alternative-id":["S0893608026002315"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108769","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Framework for hierarchical deep reinforcement learning with conceptual embedding","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108769","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108769"}}