{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:47:47Z","timestamp":1791686867673,"version":"4.3.4"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372459"],"award-info":[{"award-number":["62372459"]}],"id":[{"id":"10.13039\/501100001809","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":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109507","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T23:44:42Z","timestamp":1786491882000},"page":"109507","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["DECHRL: Empowerment-driven delay-aware causal hierarchical reinforcement learning"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6261-9585","authenticated-orcid":false,"given":"Chenran","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dianxi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengzhu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaowen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7109-5559","authenticated-orcid":false,"given":"Chunping","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8398-5612","authenticated-orcid":false,"given":"Shaowu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109507_bib0001","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.patrec.2021.06.022","article-title":"Blind decision making: Reinforcement learning with delayed observations","volume":"150","author":"Agarwal","year":"2021","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2026.109507_bib0002","series-title":"Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, december 4\u20139, 2017, long beach, CA, USA","first-page":"5048","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017"},{"key":"10.1016\/j.neunet.2026.109507_bib0003","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"The option-critic architecture","volume":"vol. 31","author":"Bacon","year":"2017"},{"key":"10.1016\/j.neunet.2026.109507_bib0004","series-title":"8th international conference on learning representations, ICLR 2020, addis ababa, ethiopia, april 26\u201330, 2020","article-title":"A meta-transfer objective for learning to disentangle causal mechanisms","author":"Bengio","year":"2020"},{"key":"10.1016\/j.neunet.2026.109507_bib0005","unstructured":"Bharadhwaj, H., Babaeizadeh, M., Erhan, D., & Levine, S. (2022). Information prioritization through empowerment in visual model-based RL. arXiv: 2204.08585."},{"key":"10.1016\/j.neunet.2026.109507_bib0006","series-title":"International conference on learning representations","article-title":"Reinforcement learning with random delays","author":"Bouteiller","year":"2020"},{"issue":"1\u20132","key":"10.1016\/j.neunet.2026.109507_bib0007","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/S0004-3702(00)00033-3","article-title":"Stochastic dynamic programming with factored representations","volume":"121","author":"Boutilier","year":"2000","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109507_bib0008","unstructured":"Cao, H., Feng, F., Fang, M., Dong, S., Yang, T., Huo, J., & Gao, Y. (2025). Towards empowerment gain through causal structure learning in model-based rl. arXiv: 2502.10077."},{"key":"10.1016\/j.neunet.2026.109507_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107318","article-title":"Hcpi-hrl: Human causal perception and inference-driven hierarchical reinforcement learning","volume":"187","author":"Chen","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109507_bib0010","article-title":"Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks","author":"Chevalier-Boisvert","year":"2023","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109507_bib0011","unstructured":"Choi, J., Sharma, A., Lee, H., Levine, S., & Gu, S. S. (2021). Variational empowerment as representation learning for goal-based reinforcement learning. arXiv: 2106.01404."},{"key":"10.1016\/j.neunet.2026.109507_bib0012","article-title":"Granger causal interaction skill chains","author":"Chuck","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109507_bib0013","series-title":"Conference on causal learning and reasoning","first-page":"178","article-title":"Disentangling controlled effects for hierarchical reinforcement learning","author":"Corcoll","year":"2022"},{"key":"10.1016\/j.neunet.2026.109507_bib0014","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., & Levine, S. (2018). Diversity is all you need: Learning skills without a reward function. arXiv: 1802.06070."},{"key":"10.1016\/j.neunet.2026.109507_bib0015","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., & Levine, S. (2020). D4rl: Datasets for deep data-driven reinforcement learning. arXiv: 2004.07219."},{"issue":"3","key":"10.1016\/j.neunet.2026.109507_bib0016","doi-asserted-by":"crossref","first-page":"424","DOI":"10.2307\/1912791","article-title":"Investigating causal relations by econometric models and cross-spectral methods","volume":"37","author":"Granger","year":"1969","journal-title":"Econometrica: Journal of the Econometric Society"},{"key":"10.1016\/j.neunet.2026.109507_bib0017","unstructured":"Gregor, K., Rezende, D. J., & Wierstra, D. (2016). Variational intrinsic control. arXiv: 1611.07507."},{"key":"10.1016\/j.neunet.2026.109507_bib0018","article-title":"Off-policy reinforcement learning with delayed rewards","author":"Han","year":"2021","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109507_bib0019","first-page":"20064","article-title":"Causality-driven hierarchical structure discovery for reinforcement learning","volume":"35","author":"Hu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109507_bib0020","article-title":"Reinforcement learning from delayed observations via world models","author":"Karamzade","year":"2024","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109507_bib0021","unstructured":"Ke, N. R., Bilaniuk, O., Goyal, A., Bauer, S., Larochelle, H., Sch\u00f6lkopf, B., Mozer, M. C., Pal, C., & Bengio, Y. (2019). Learning neural causal models from unknown interventions. arXiv: 1910.01075."},{"key":"10.1016\/j.neunet.2026.109507_bib0022","unstructured":"Kim, W., Kim, J., & Sung, Y. (2023). Lesson: Learning to integrate exploration strategies for reinforcement learning via an option framework. arXiv: 2310.03342."},{"key":"10.1016\/j.neunet.2026.109507_bib0023","series-title":"CoRL 2023 workshop on learning effective abstractions for planning (LEAP)","article-title":"Scale: Causal learning and discovery of robot manipulation skills using simulation","author":"Lee","year":"2023"},{"key":"10.1016\/j.neunet.2026.109507_bib0024","unstructured":"Levy, A., Konidaris, G., Platt, R., & Saenko, K. (2017). Learning multi-level hierarchies with hindsight. arXiv: 1712.00948."},{"key":"10.1016\/j.neunet.2026.109507_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106825","article-title":"Highly valued subgoal generation for efficient goal-conditioned reinforcement learning","volume":"181","author":"Li","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109507_bib0026","series-title":"International conference on machine learning","first-page":"13528","article-title":"Delayed reinforcement learning by imitation","author":"Liotet","year":"2022"},{"key":"10.1016\/j.neunet.2026.109507_bib0027","series-title":"2021 International joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Learning a belief representation for delayed reinforcement learning","author":"Liotet","year":"2021"},{"key":"10.1016\/j.neunet.2026.109507_bib0028","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109507_bib0029","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","volume":"28","author":"Mohamed","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109507_bib0030","series-title":"Proceedings of the 30th ACM international conference on information & knowledge management","first-page":"1346","article-title":"Revisiting state augmentation methods for reinforcement learning with stochastic delays","author":"Nath","year":"2021"},{"key":"10.1016\/j.neunet.2026.109507_bib0031","series-title":"Joint european conference on machine learning and knowledge discovery in databases","first-page":"216","article-title":"Variable-agnostic causal exploration for reinforcement learning","author":"Nguyen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109507_bib0032","series-title":"Models, reasoning and inference","first-page":"3","volume":"19","author":"Pearl","year":"2000"},{"key":"10.1016\/j.neunet.2026.109507_bib0033","series-title":"Elements of causal inference: Foundations and learning algorithms","author":"Peters","year":"2017"},{"key":"10.1016\/j.neunet.2026.109507_bib0034","series-title":"2010\u202fIEEE\/RSJ International conference on intelligent robots and systems","first-page":"3226","article-title":"Control delay in reinforcement learning for real-time dynamic systems: A memoryless approach","author":"Schuitema","year":"2010"},{"key":"10.1016\/j.neunet.2026.109507_bib0035","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109507_bib0036","unstructured":"Sharma, A., Gu, S., Levine, S., Kumar, V., & Hausman, K. (2019). Dynamics-aware unsupervised discovery of skills. arXiv: 1907.01657."},{"key":"10.1016\/j.neunet.2026.109507_bib0037","first-page":"7156","article-title":"Hierarchical reinforcement learning for zero-shot generalization with subtask dependencies","volume":"31","author":"Sohn","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109507_bib0038","series-title":"Causation, prediction, and search","author":"Spirtes","year":"2000"},{"issue":"1","key":"10.1016\/j.neunet.2026.109507_bib0039","first-page":"126","article-title":"Reinforcement learning","volume":"11","author":"Sutton","year":"1999","journal-title":"Journal of Cognitive Neuroscience"},{"key":"10.1016\/j.neunet.2026.109507_bib0040","series-title":"ICLR 2024","article-title":"Addressing signal delay in deep reinforcement learning","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109507_bib0041","article-title":"Qwen3 technical report","author":"Yang","year":"2025","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.109507_bib0042","series-title":"International Conference on Learning Representations","article-title":"Delay-aware reinforcement learning: Insights from delay distributional perspective","author":"Yu","year":"2025"},{"key":"10.1016\/j.neunet.2026.109507_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108275","article-title":"D3HRL: A distributed hierarchical reinforcement learning approach based on causal discovery and spurious correlation detection","volume":"195","author":"Zhao","year":"2026","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009652?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009652?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:24:56Z","timestamp":1791685496000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009652"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":43,"alternative-id":["S0893608026009652"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109507","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DECHRL: Empowerment-driven delay-aware causal hierarchical reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109507","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":"109507"}}