{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:05:21Z","timestamp":1790111121894,"version":"4.0.1"},"reference-count":70,"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":["62495090,62495093"],"award-info":[{"award-number":["62495090,62495093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"publisher","award":["BK20243039"],"award-info":[{"award-number":["BK20243039"]}],"id":[{"id":"10.13039\/501100004608","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.2026.109343","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:04:09Z","timestamp":1783440249000},"page":"109343","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Any-step dynamics model improves future predictions for offline reinforcement learning via hierarchical roll-out"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3321-3538","authenticated-orcid":false,"given":"Haoxin","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9908-5303","authenticated-orcid":false,"given":"Yi-Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhilong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxing","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109343_bib0001","series-title":"Proceedings of the 37th international conference on machine learning (ICML\u201920)","article-title":"An optimistic perspective on offline reinforcement learning","author":"Agarwal","year":"2020"},{"key":"10.1016\/j.neunet.2026.109343_bib0002","series-title":"Advances in neural information processing systems 34 (neurIPS\u201921)","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","author":"An","year":"2021"},{"key":"10.1016\/j.neunet.2026.109343_bib0003","unstructured":"Asadi, K., Cater, E., Misra, D., & Littman, M. L. (2018). Towards a simple approach to multi-step model-based reinforcement learning. arXiv: 1811.00128."},{"key":"10.1016\/j.neunet.2026.109343_bib0004","unstructured":"Asadi, K., Misra, D., Kim, S., & Littman, M. L. (2019). Combating the compounding-error problem with a multi-step model. arXiv: 1905.13320."},{"key":"10.1016\/j.neunet.2026.109343_bib0005","series-title":"10th international conference on learning representations (ICLR\u201922)","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","author":"Bai","year":"2022"},{"key":"10.1016\/j.neunet.2026.109343_bib0006","series-title":"Advances in neural information processing systems 36 (neurIPS\u201923)","article-title":"Adversarial model for offline reinforcement learning","author":"Bhardwaj","year":"2023"},{"key":"10.1016\/j.neunet.2026.109343_bib0007","series-title":"Advances in neural information processing systems 31 (neurIPS\u201918)","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"Buckman","year":"2018"},{"key":"10.1016\/j.neunet.2026.109343_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijepes.2025.110982","article-title":"Resilient memory sampled-data controller for synchronization of semi-Markovian jump competitive neural networks with mixed delays","volume":"171","author":"Chandrasekar","year":"2025","journal-title":"International Journal of Electrical Power & Energy Systems"},{"key":"10.1016\/j.neunet.2026.109343_bib0009","unstructured":"Che, T., Lu, Y., Tucker, G., Bhupatiraju, S., Gu, S., Levine, S., & Bengio, Y. (2018). Combining model-based and model-free RL via multi-step control variates. https:\/\/openreview.net. https:\/\/openreview.net\/forum?id=HkPCrEZ0Z."},{"key":"10.1016\/j.neunet.2026.109343_bib0010","series-title":"Proceedings of the 41st international conference on machine learning (ICML\u201924)","article-title":"Offline transition modeling via contrastive energy learning","author":"Chen","year":"2024"},{"issue":"12","key":"10.1016\/j.neunet.2026.109343_bib0011","doi-asserted-by":"crossref","first-page":"15260","DOI":"10.1109\/TPAMI.2023.3317131","article-title":"Offline model-based adaptable policy learning for decision-making in out-of-support regions","volume":"45","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109343_bib0012","series-title":"Advances in neural information processing systems 36 (neurIPS\u201923)","article-title":"Adversarial counterfactual environment model learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109343_bib0013","series-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP\u201914)","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.neunet.2026.109343_bib0014","series-title":"Advances in neural information processing systems 31 (neurIPS\u201918)","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"Chua","year":"2018"},{"key":"10.1016\/j.neunet.2026.109343_bib0015","series-title":"8th international conference on learning representations (ICLR\u201920)","article-title":"Model-augmented actor-critic: Backpropagating through paths","author":"Clavera","year":"2020"},{"issue":"2","key":"10.1016\/j.neunet.2026.109343_bib0016","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cognitive Science"},{"key":"10.1016\/j.neunet.2026.109343_bib0017","unstructured":"Feinberg, V., Wan, A., Stoica, I., Jordan, M. I., Gonzalez, J. E., & Levine, S. (2018). Model-based value estimation for efficient model-free reinforcement learning. arXiv: 1803.00101."},{"key":"10.1016\/j.neunet.2026.109343_bib0018","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., & Levine, S. (2020). D4RL: Datasets for deep data-driven reinforcement learning. arXiv: 2004.07219."},{"key":"10.1016\/j.neunet.2026.109343_bib0019","series-title":"Advances in neural information processing systems 34 (neurIPS\u201921)","article-title":"A minimalist approach to offline reinforcement learning","author":"Fujimoto","year":"2021"},{"key":"10.1016\/j.neunet.2026.109343_bib0020","series-title":"Proceedings of the 35th international conference on machine learning (ICML\u201918)","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.neunet.2026.109343_bib0021","series-title":"Proceedings of the 36th international conference on machine learning (ICML\u201919)","article-title":"Off-policy deep reinforcement learning without exploration","author":"Fujimoto","year":"2019"},{"key":"10.1016\/j.neunet.2026.109343_bib0022","series-title":"The 11th international conference on learning representations (ICLR\u201923)","article-title":"Extreme q-learning: Maxent RL without entropy","author":"Garg","year":"2023"},{"key":"10.1016\/j.neunet.2026.109343_bib0023","series-title":"Proceedings of the 35th international conference on machine learning (ICML\u201918)","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.neunet.2026.109343_bib0024","series-title":"Proceedings of the 30th AAAI conference on artificial intelligence (aaai\u201916)","article-title":"Deep reinforcement learning with double q-learning","author":"Hasselt","year":"2016"},{"key":"10.1016\/j.neunet.2026.109343_bib0025","series-title":"Advances in neural information processing systems 32 (neurIPS\u201919)","article-title":"When to trust your model: Model-based policy optimization","author":"Janner","year":"2019"},{"key":"10.1016\/j.neunet.2026.109343_bib0026","series-title":"The 11th international conference on learning representations (ICLR\u201923)","article-title":"Conservative Bayesian model-based value expansion for offline policy optimization","author":"Jeong","year":"2023"},{"key":"10.1016\/j.neunet.2026.109343_bib0027","series-title":"Proceedings of the 38th international conference on machine learning (ICML\u201921)","article-title":"Is pessimism provably efficient for offline RL?","author":"Jin","year":"2021"},{"key":"10.1016\/j.neunet.2026.109343_bib0028","series-title":"Robotics: Science and systems XV (RSS\u201919)","article-title":"Differentiable algorithm networks for composable robot learning","author":"Karkus","year":"2019"},{"key":"10.1016\/j.neunet.2026.109343_bib0029","series-title":"Advances in neural information processing systems 33 (neurIPS\u201920)","article-title":"Morel: Model-based offline reinforcement learning","author":"Kidambi","year":"2020"},{"issue":"6","key":"10.1016\/j.neunet.2026.109343_bib0030","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":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.109343_bib0031","series-title":"Advances in neural information processing systems 32 (neurIPS\u201919)","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","author":"Kumar","year":"2019"},{"key":"10.1016\/j.neunet.2026.109343_bib0032","series-title":"Advances in neural information processing systems 33 (neurIPS\u201920)","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020"},{"key":"10.1016\/j.neunet.2026.109343_bib0033","series-title":"Proceedings of the 37th international conference on machine learning (ICML\u201920)","article-title":"Bidirectional model-based policy optimization","author":"Lai","year":"2020"},{"key":"10.1016\/j.neunet.2026.109343_bib0034","series-title":"Advances in neural information processing systems 30 (neurIPS\u201917)","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Lakshminarayanan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109343_bib0035","series-title":"Proceedings of the 26th european conference on artificial intelligence (ECAI\u201923)","article-title":"Model-based reinforcement learning with multi-step plan value estimation","author":"Lin","year":"2023"},{"key":"10.1016\/j.neunet.2026.109343_bib0036","series-title":"The 13th international conference on learning representations (ICLR\u201925)","article-title":"Any-step dynamics model improves future predictions for online and offline reinforcement learning","author":"Lin","year":"2025"},{"issue":"2","key":"10.1016\/j.neunet.2026.109343_bib0037","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1109\/TG.2021.3071162","article-title":"Efficient reinforcement learning for starcraft by abstract forward models and transfer learning","volume":"14","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Games"},{"issue":"3","key":"10.1016\/j.neunet.2026.109343_bib0038","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.1109\/TASE.2023.3288037","article-title":"Hierarchical reinforcement learning integrating with human knowledge for practical robot skill learning in complex multi-stage manipulation","volume":"21","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"10.1016\/j.neunet.2026.109343_bib0039","series-title":"Proceedings of the 35th uncertainty in artificial intelligence conference (UAI\u201920)","article-title":"Off-policy policy gradient with stationary distribution correction","author":"Liu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109343_bib0040","series-title":"The 10th international conference on learning representations (ICLR\u201922)","article-title":"Revisiting design choices in offline model based reinforcement learning","author":"Lu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109343_bib0041","series-title":"The 12th international conference on learning representations (ICLR\u201924)","article-title":"Reward-consistent dynamics models are strongly generalizable for offline reinforcement learning","author":"Luo","year":"2024"},{"key":"10.1016\/j.neunet.2026.109343_bib0042","series-title":"7th international conference on learning representations (ICLR\u201919)","article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","author":"Luo","year":"2019"},{"key":"10.1016\/j.neunet.2026.109343_bib0043","first-page":"80:1","article-title":"Temporal abstraction in reinforcement learning with the successor representation","volume":"24","author":"Machado","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109343_bib0044","series-title":"Proceedings of the 33nd international conference on machine learning (ICML\u201916)","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"issue":"7540","key":"10.1016\/j.neunet.2026.109343_bib0045","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.2026.109343_bib0046","series-title":"3rd IEEE international conference on robotic computing (IRC\u201919)","article-title":"Review of deep reinforcement learning for robot manipulation","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.neunet.2026.109343_bib0047","unstructured":"Okada, M., Rigazio, L., & Aoshima, T. (2017). Path integral networks: End-to-end differentiable optimal control. arXiv: 1706.09597."},{"key":"10.1016\/j.neunet.2026.109343_bib0048","series-title":"Advances in neural information processing systems 33 (neurIPS\u201920)","article-title":"Trust the model when it is confident: Masked model-based actor-critic","author":"Pan","year":"2020"},{"key":"10.1016\/j.neunet.2026.109343_bib0049","series-title":"Proceedings of the 18th international conference on machine learning (ICML\u201901)","article-title":"Off-policy temporal difference learning with function approximation","author":"Precup","year":"2001"},{"key":"10.1016\/j.neunet.2026.109343_bib0050","series-title":"Advances in neural information processing systems 35 (neurIPS\u201922)","article-title":"NeoRL: A near real-world benchmark for offline reinforcement learning","author":"Qin","year":"2022"},{"key":"10.1016\/j.neunet.2026.109343_bib0051","series-title":"Advances in neural information processing systems 35 (neurIPS\u201922)","article-title":"RAMBO-RL: Robust adversarial model-based offline reinforcement learning","author":"Rigter","year":"2022"},{"key":"10.1016\/j.neunet.2026.109343_bib0052","series-title":"Proceedings of the 32nd international conference on machine learning (ICML\u201915)","article-title":"Trust region policy optimization","author":"Schulman","year":"2015"},{"key":"10.1016\/j.neunet.2026.109343_bib0053","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., Lillicrap, T. P., Simonyan, K., & Hassabis, D. (2017). Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv: 1712.01815."},{"key":"10.1016\/j.neunet.2026.109343_bib0054","series-title":"Proceedings of the 35th international conference on machine learning (ICML\u201918)","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","author":"Srinivas","year":"2018"},{"key":"10.1016\/j.neunet.2026.109343_bib0055","series-title":"Proceedings of the 40th international conference on machine learning (ICML\u201923)","article-title":"Model-bellman inconsistency for model-based offline reinforcement learning","author":"Sun","year":"2023"},{"key":"10.1016\/j.neunet.2026.109343_bib0056","series-title":"Proceedings of the 7th international conference on machine learning (ICML\u201990)","article-title":"Integrated architectures for learning, planning, and reacting based on approximating dynamic programming","author":"Sutton","year":"1990"},{"key":"10.1016\/j.neunet.2026.109343_bib0057","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2026.109343_bib0058","doi-asserted-by":"crossref","first-page":"1879","DOI":"10.1002\/mma.8774","article-title":"Synchronization of Markovian jump neural networks for sampled data control systems with additive delay components: Analysis of image encryption technique","volume":"49","author":"Tamil Thendral","year":"2026","journal-title":"Mathematical Methods in the Applied Sciences"},{"key":"10.1016\/j.neunet.2026.109343_bib0059","series-title":"IEEE\/RSJ international conference on intelligent robots and systems (iros\u201920)","article-title":"Mujoco: A physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.neunet.2026.109343_bib0060","series-title":"Advances in neural information processing systems 30 (neurIPS\u201917)","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2026.109343_bib0061","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104654","article-title":"Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey","volume":"164","author":"Wu","year":"2024","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"10","key":"10.1016\/j.neunet.2026.109343_bib0062","doi-asserted-by":"crossref","first-page":"6968","DOI":"10.1109\/TPAMI.2021.3096966","article-title":"Error bounds of imitating policies and environments for reinforcement learning","volume":"44","author":"Xu","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2026.109343_bib0063","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.1109\/TASE.2022.3190901","article-title":"Intelligent path planning of underwater robot based on reinforcement learning","volume":"20","author":"Yang","year":"2023","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"10.1016\/j.neunet.2026.109343_bib0064","series-title":"Advances in neural information processing systems 34 (neurIPS\u201921)","article-title":"COMBO: Conservative offline model-based policy optimization","author":"Yu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109343_bib0065","series-title":"Advances in neural information processing systems 33 (neurIPS\u201920)","article-title":"MOPO: Model-based offline policy optimization","author":"Yu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109343_bib0066","series-title":"Proceedings of the 38th international conference on neural information processing systems (NIPS\u201924)","article-title":"Q-distribution guided q-learning for offline reinforcement learning: Uncertainty penalized q-value via consistency model","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109343_bib0067","unstructured":"Zhang, Z., Chen, R., Ye, J., Sun, Y., Wang, P., Pang, J., Li, K., Liu, T., Lin, H., Yu, Y., & Zhou, Z. (2024b). WHALE: Towards generalizable and scalable world models for embodied decision-making. arXiv: 2411.05619."},{"key":"10.1016\/j.neunet.2026.109343_bib0068","series-title":"The fourteenth international conference on learning representations (ICLR\u201926)","article-title":"Hierarchical value-decomposed offline reinforcement learning for whole-body control","author":"Zhang","year":"2026"},{"key":"10.1016\/j.neunet.2026.109343_bib0069","series-title":"The twelfth international conference on learning representations","article-title":"Flow to better: Offline preference-based reinforcement learning via preferred trajectory generation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109343_bib0070","unstructured":"Zhu, Z.-M., Chen, X.-H., Tian, H.-L., Zhang, K., & Yu, Y. (2022). Offline reinforcement learning with causal structured world models. arXiv: 2206.01474."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008026?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008026?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:07:18Z","timestamp":1790107638000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":70,"alternative-id":["S0893608026008026"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109343","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":"Any-step dynamics model improves future predictions for offline reinforcement learning via hierarchical roll-out","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109343","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":"109343"}}