{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T16:27:07Z","timestamp":1786638427356,"version":"build-2736575974"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108868","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T08:37:30Z","timestamp":1773909450000},"page":"108868","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A representational framework for learning and encoding structurally enriched trajectories in complex agent environments"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9186-3092","authenticated-orcid":false,"given":"Corina","family":"C\u0103t\u0103r\u0103u-Cotutiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4180-1261","authenticated-orcid":false,"given":"Esther","family":"Mondrag\u00f3n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3306-695X","authenticated-orcid":false,"given":"Eduardo","family":"Alonso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108868_bib0001","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"The option-critic architecture","volume":"vol. 31","author":"Bacon","year":"2017"},{"issue":"8","key":"10.1016\/j.neunet.2026.108868_bib0002","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2026.108868_bib0003","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.cognition.2008.08.011","article-title":"Hierarchically organized behavior and its neural foundations: A reinforcement learning perspective","volume":"113","author":"Botvinick","year":"2009","journal-title":"Cognition"},{"key":"10.1016\/j.neunet.2026.108868_bib0004","series-title":"Epia conference on artificial intelligence","first-page":"38","article-title":"Aigenc: Ai generalisation via creativity","author":"Catarau-Cotutiu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108868_bib0005","doi-asserted-by":"crossref","unstructured":"Chen, E., Chen, X., & Jing, W. (2024). Data-driven knowledge transfer in batch q* learning. arXiv: 2404.15209.","DOI":"10.2139\/ssrn.4787816"},{"key":"10.1016\/j.neunet.2026.108868_bib0006","series-title":"35th international conference on machine learning","first-page":"1009","article-title":"Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings","author":"Co-Reyes","year":"2018"},{"key":"10.1016\/j.neunet.2026.108868_bib0007","unstructured":"D\u2019Eramo, C., Tateo, D., Bonarini, A., Restelli, M., & Peters, J. (2024). Sharing knowledge in multi-task deep reinforcement learning. arXiv: 2401.09561."},{"key":"10.1016\/j.neunet.2026.108868_bib0008","series-title":"39th international conference on machine learning","first-page":"12004","article-title":"Goal misgeneralization in deep reinforcement learning","author":"Di Langosco","year":"2022"},{"issue":"47","key":"10.1016\/j.neunet.2026.108868_bib0009","doi-asserted-by":"crossref","first-page":"29381","DOI":"10.1073\/pnas.1912330117","article-title":"Computational evidence for hierarchically structured reinforcement learning in humans","volume":"117","author":"Eckstein","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2026.108868_bib0010","series-title":"Advances in neural information processing systems","first-page":"35603","article-title":"Contrastive learning as goal-conditioned reinforcement learning","volume":"vol. 35","author":"Eysenbach","year":"2022"},{"key":"10.1016\/j.neunet.2026.108868_bib0011","series-title":"34th international conference on machine learning","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"issue":"1","key":"10.1016\/j.neunet.2026.108868_bib0012","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/s42256-024-00950-3","article-title":"Sequential memory improves sample and memory efficiency in episodic control","volume":"7","author":"Freire","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108868_bib0013","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.neunet.2026.108868_bib0014","series-title":"The people, place, and space reader","first-page":"56","article-title":"The theory of affordances:(1979)","author":"Gibson","year":"2014"},{"key":"10.1016\/j.neunet.2026.108868_bib0015","series-title":"International conference on machine learning","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"10.1016\/j.neunet.2026.108868_bib0016","unstructured":"Hafner, D., Lillicrap, T., Ba, J., & Norouzi, M. (2019). Dream to control: Learning behaviors by latent imagination. arXiv: 1912.01603."},{"issue":"8","key":"10.1016\/j.neunet.2026.108868_bib0017","doi-asserted-by":"crossref","first-page":"2534","DOI":"10.1111\/cogs.12688","article-title":"The outcome-representation learning model: A novel reinforcement learning model of the iowa gambling task","volume":"42","author":"Haines","year":"2018","journal-title":"Cognitive Science"},{"key":"10.1016\/j.neunet.2026.108868_bib0018","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.108868_bib0019","unstructured":"Higgins, I., Amos, D., Pfau, D., Racaniere, S., Matthey, L., Rezende, D., & Lerchner, A. (2018). Towards a definition of disentangled representations. arXiv: 1812.02230."},{"key":"10.1016\/j.neunet.2026.108868_bib0020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s004260000032","article-title":"Hierarchical coding in the perception and memory of spatial layouts","volume":"64","author":"Hommel","year":"2000","journal-title":"Psychological Research"},{"key":"10.1016\/j.neunet.2026.108868_bib0021","unstructured":"Jain, A., Szot, A., & Lim, J. J. (2020). Generalization to new actions in reinforcement learning. arXiv: 2011.01928."},{"key":"10.1016\/j.neunet.2026.108868_bib0022","series-title":"2024 International joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Causal graph representation learning for outcome-oriented link prediction","author":"Jin","year":"2024"},{"key":"10.1016\/j.neunet.2026.108868_bib0023","series-title":"IJCAI","first-page":"1094","article-title":"Learning to achieve goals","volume":"vol. 2","author":"Kaelbling","year":"1993"},{"key":"10.1016\/j.neunet.2026.108868_bib0024","series-title":"2021\u202fIEEE International conference on robotics and automation (ICRA)","first-page":"14291","article-title":"What can i do here? learning new skills by imagining visual affordances","author":"Khazatsky","year":"2021"},{"issue":"6","key":"10.1016\/j.neunet.2026.108868_bib0025","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: A survey","volume":"23","author":"Kiran","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108868_bib0026","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.neunet.2026.108868_bib0027","series-title":"Cst: Constructing skill trees by demonstration","author":"Konidaris","year":"2011"},{"key":"10.1016\/j.neunet.2026.108868_bib0028","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108868_bib0029","doi-asserted-by":"crossref","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behavioral and Brain Sciences"},{"key":"10.1016\/j.neunet.2026.108868_bib0030","series-title":"Neo4j graph data modeling","author":"Lal","year":"2015"},{"key":"10.1016\/j.neunet.2026.108868_bib0031","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.neunet.2018.07.006","article-title":"State representation learning for control: An overview","volume":"108","author":"Lesort","year":"2018","journal-title":"Neural Networks"},{"issue":"4\u20135","key":"10.1016\/j.neunet.2026.108868_bib0032","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1177\/0278364917710318","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"37","author":"Levine","year":"2018","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.neunet.2026.108868_bib0033","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1613\/jair.1.15703","article-title":"Structure in deep reinforcement learning: A survey and open problems","volume":"79","author":"Mohan","year":"2024","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"17","key":"10.1016\/j.neunet.2026.108868_bib0034","doi-asserted-by":"crossref","first-page":"3636","DOI":"10.1523\/JNEUROSCI.1079-21.2022","article-title":"The neural bases of action-outcome learning in humans","volume":"42","author":"Morris","year":"2022","journal-title":"Journal of Neuroscience"},{"key":"10.1016\/j.neunet.2026.108868_bib0035","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.cognition.2016.11.009","article-title":"Hierarchical organization in visual working memory: From global ensemble to individual object structure","volume":"159","author":"Nie","year":"2017","journal-title":"Cognition"},{"issue":"10","key":"10.1016\/j.neunet.2026.108868_bib0036","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1038\/s41593-019-0470-8","article-title":"Learning task-state representations","volume":"22","author":"Niv","year":"2019","journal-title":"Nature Neuroscience"},{"issue":"5","key":"10.1016\/j.neunet.2026.108868_bib0037","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.2026.108868_bib0038","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. arXiv: 2204.06125, 1(2), 3."},{"issue":"12","key":"10.1016\/j.neunet.2026.108868_bib0039","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1016\/j.tics.2024.07.005","article-title":"The dimensions of dimensionality","volume":"28","author":"Roads","year":"2024","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.neunet.2026.108868_bib0040","series-title":"Advances in neural information processing systems","first-page":"13045","article-title":"Outcome-driven reinforcement learning via variational inference","volume":"vol. 34","author":"Rudner","year":"2021"},{"key":"10.1016\/j.neunet.2026.108868_bib0041","doi-asserted-by":"crossref","unstructured":"Sancho, V., Blackmore, L., Chamberlain, B., & Hollenbeck, B. (2024). Neural contextual cascade in large language models for hierarchical concept representation. Authorea Preprints.","DOI":"10.36227\/techrxiv.173397940.09536132\/v1"},{"issue":"1","key":"10.1016\/j.neunet.2026.108868_bib0042","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"3","key":"10.1016\/j.neunet.2026.108868_bib0043","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.newideapsych.2013.04.003","article-title":"Representation and learning in motor action\u2013bridges between experimental research and cognitive robotics","volume":"31","author":"Schack","year":"2013","journal-title":"New Ideas in Psychology"},{"key":"10.1016\/j.neunet.2026.108868_bib0044","series-title":"International conference on machine learning","first-page":"1312","article-title":"Universal value function approximators","author":"Schaul","year":"2015"},{"issue":"4","key":"10.1016\/j.neunet.2026.108868_bib0045","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1037\/0096-3445.135.4.623","article-title":"Hierarchical control of cognitive processes: switching tasks in sequences","volume":"135","author":"Schneider","year":"2006","journal-title":"Journal of Experimental Psychology: General"},{"issue":"7676","key":"10.1016\/j.neunet.2026.108868_bib0046","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.2026.108868_bib0047","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556."},{"key":"10.1016\/j.neunet.2026.108868_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106645","article-title":"Gtc: Gnn-transformer co-contrastive learning for self-supervised heterogeneous graph representation","volume":"181","author":"Sun","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108868_bib0049","series-title":"Reinforcement learning: An introduction","volume":"vol. 1","author":"Sutton","year":"1998"},{"issue":"1\u20132","key":"10.1016\/j.neunet.2026.108868_bib0050","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.2026.108868_bib0051","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Deep reinforcement learning with double q-learning","volume":"vol. 30","author":"Van Hasselt","year":"2016"},{"key":"10.1016\/j.neunet.2026.108868_bib0052","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"1726","article-title":"Self-supervised heterogeneous graph neural network with co-contrastive learning","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108868_bib0053","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Machine learning"},{"key":"10.1016\/j.neunet.2026.108868_bib0054","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.49547","article-title":"Ten simple rules for the computational modeling of behavioral data","volume":"8","author":"Wilson","year":"2019","journal-title":"eLife"},{"key":"10.1016\/j.neunet.2026.108868_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.bbr.2022.114025","article-title":"Cognitive control is modulated by hierarchical complexity of task switching: An event-related potential study","volume":"434","author":"Wu","year":"2022","journal-title":"Behavioural Brain Research"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003291?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003291?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:26:17Z","timestamp":1786634777000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003291"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":55,"alternative-id":["S0893608026003291"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108868","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A representational framework for learning and encoding structurally enriched trajectories in complex agent environments","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108868","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108868"}}