{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T08:37:03Z","timestamp":1792831023876,"version":"4.5.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1007\/s10489-026-07485-7","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T01:30:55Z","timestamp":1790213455000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HALSI: Hierarchical adaptive latent skill inference for temporal abstraction in reinforcement learning"],"prefix":"10.1007","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1397-1204","authenticated-orcid":false,"given":"Xiaxi","family":"Si","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ping","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"7485_CR1","unstructured":"Freed B, Venkatraman S, Sartoretti GA, Schneider J, Choset H (2023) Learning temporally abstractworld models without online experimentation. In: International conference on machine learning, ICML, pp 10338\u201310356"},{"key":"7485_CR2","unstructured":"Hakhamaneshi K, Zhao R, Zhan A, Abbeel P, Laskin M (2021) Hierarchical few-shot imitation with skill transition models. arXiv preprint arXiv:2107.08981"},{"key":"7485_CR3","unstructured":"Nasiriany S, Gao T, Mandlekar A, Zhu Y (2022) Learning and retrieval from prior data for skill-based imitation learning. arXiv preprint arXiv:2210.11435"},{"key":"7485_CR4","doi-asserted-by":"crossref","unstructured":"Kim WK, Yoo M, Woo H (2024) Robust policy learning via offline skill diffusion, vol 38, AAAI Press, pp 13177\u201313184","DOI":"10.1609\/aaai.v38i12.29217"},{"key":"7485_CR5","unstructured":"Nachum O, Gu SS, Lee H, Levine S (2018) Data-efficient hierarchical reinforcement learning. Adv Neural Inf Process Syst, p 31"},{"key":"7485_CR6","unstructured":"Vezhnevets AS, Osindero S, Schaul T, Heess N, Jaderberg M, Silver D, Kavukcuoglu K (2017) Feudal networks for hierarchical reinforcement learning. In: International conference on machine learning, ICML, pp 3540\u20133549"},{"issue":"4","key":"7485_CR7","doi-asserted-by":"publisher","first-page":"4483","DOI":"10.1007\/s10489-022-03643-9","volume":"53","author":"Z Qiao","year":"2023","unstructured":"Qiao Z, Ke L, Wang X (2023) Traffic signal control using a cooperative ewma-based multi-agent reinforcement learning. Appl Intell 53(4):4483\u20134498","journal-title":"Appl Intell"},{"key":"7485_CR8","doi-asserted-by":"crossref","unstructured":"Zhao X, Ding S, An Y, Jia W (2019) Applications of asynchronous deep reinforcement learning based on dynamic updating weights: X. zhao et al. Appl Intell 49(2):581\u2013591","DOI":"10.1007\/s10489-018-1296-x"},{"key":"7485_CR9","doi-asserted-by":"publisher","first-page":"120560","DOI":"10.1016\/j.ins.2024.120560","volume":"669","author":"X Wang","year":"2024","unstructured":"Wang X, Ke L, Zhang G, Zhu D (2024) Adaptive mean field multi-agent reinforcement learning. Inf Sci 669:120560","journal-title":"Inf Sci"},{"key":"7485_CR10","doi-asserted-by":"crossref","unstructured":"Ding S, Zhao X, Xu X, Sun T, Jia W (2019) An effective asynchronous framework for small scale reinforcement learning problems: S. ding et al. Appl Intell 49(12):4303\u20134318","DOI":"10.1007\/s10489-019-01501-9"},{"key":"7485_CR11","unstructured":"Yang X, Calandra R, Held D (2023) Residual skill policies: Learning an adaptable skill-based action space for reinforcement learning for robotics. Robotics Science and Systems (RSS)"},{"issue":"4","key":"7485_CR12","doi-asserted-by":"publisher","first-page":"3625","DOI":"10.1109\/LRA.2024.3368231","volume":"9","author":"C Hao","year":"2024","unstructured":"Hao C, Weaver C, Tang C, Kawamoto K, Tomizuka M, Zhan W (2024) Skill-critic: Refining learned skills for hierarchical reinforcement learning. IEEE Robot Autom Lett 9(4):3625\u20133632","journal-title":"IEEE Robot Autom Lett"},{"key":"7485_CR13","unstructured":"Pertsch T, Radosavovic I, Lim JJ (2020) Accelerating reinforcement learning with learned skill priors. Conference on Robot Learning. CoRL"},{"key":"7485_CR14","doi-asserted-by":"crossref","unstructured":"Stoler B, Navarro I, Francis J, Oh J (2024) Seal: Towards safe autonomous driving via skill-enabled adversary learning for closed-loop scenario generation. arXiv preprint arXiv:2409.10320","DOI":"10.1109\/LRA.2025.3592090"},{"key":"7485_CR15","doi-asserted-by":"crossref","unstructured":"Chen WYDX (2025) Dsr: Optimization of performance lower bound for hierarchical policy with dynamical skill refinement. Front Comp Sci 0","DOI":"10.1007\/s11704-025-50561-3"},{"key":"7485_CR16","doi-asserted-by":"publisher","first-page":"110573","DOI":"10.52202\/079017-3510","volume":"37","author":"X Yu","year":"2024","unstructured":"Yu X, Dunion M, Li X, Albrecht SV (2024) Skill-aware mutual information optimisation for zero-shot generalisation in reinforcement learning. Adv Neural Inf Process Syst 37:110573\u2013110612","journal-title":"Adv Neural Inf Process Syst"},{"key":"7485_CR17","unstructured":"Wilcoxson M, Li Q, Frans K, Levine S (2024) Leveraging skills from unlabeled prior data for efficient online exploration. CoRR arXiv:2410.18076"},{"key":"7485_CR18","doi-asserted-by":"crossref","unstructured":"Li Q, Zhou Z, Levine S (2025) Reinforcement learning with action chunking. arXiv preprint arXiv:2507.07969","DOI":"10.52202\/085713-1856"},{"key":"7485_CR19","unstructured":"Li G, Tian D, Zhou H, Jiang X, Lioutikov R, Neumann G (2024) Top-erl: Transformer-based off-policy episodic reinforcement learning. arXiv preprint arXiv:2410.09536"},{"key":"7485_CR20","doi-asserted-by":"crossref","unstructured":"Liang Z, Mu Y, Ma H, Tomizuka M, Ding M, Luo P (2024) Skilldiffuser: Interpretable hierarchical planning via skill abstractions in diffusion-based task execution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16467\u201316476","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"7485_CR21","unstructured":"Chen L, Lu K, Rajeswaran A, Lee K, Grover A, Laskin M, Abbeel P, Srinivas A, Levine S (2021) Decision transformer: Reinforcement learning via sequence modeling. In: Advances in neural information processing systems, vol 34, pp 15084\u201315097"},{"key":"7485_CR22","unstructured":"Janner M, Li Q, Levine S (2021) Trajectory transformer: Model-based reinforcement learning with faster planning and a smaller model. In: International Conference on Machine Learning, ICML, pp 4900\u20134910"},{"key":"7485_CR23","doi-asserted-by":"crossref","unstructured":"Zhao TZ, Kumar V, Levine S, Finn C (2023) Learning fine-grained bimanual manipulation with low-cost hardware. arXiv preprint arXiv:2304.13705","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"7485_CR24","unstructured":"Li G, Tian D, Zhou H, Jiang X, Lioutikov R, Neumann G (2024) Top-erl: Transformer-based off-policy episodic reinforcement learning. arXiv preprint arXiv:2410.09536"},{"key":"7485_CR25","unstructured":"Bhattacharyya A, Shi H, Liu X, Kroemer O (2022) Edm: Diffusion-based policy for offline reinforcement learning. In: Advances in neural information processing systems, vol 35, pp 18319\u201318332"},{"key":"7485_CR26","unstructured":"Chi E, Pitis S, Ghasemipour SKS, Finn C, Levine S (2023) Diffusion policies as an expressive policy class for offline reinforcement learning. In: International Conference on Learning Representations, ICLR"},{"key":"7485_CR27","doi-asserted-by":"crossref","unstructured":"Qiao R, Cheng J, Dai X, Tian Y, Lv Y (2025) Offline reinforcement learning with discrete diffusion skills","DOI":"10.1109\/TAI.2026.3746377"},{"key":"7485_CR28","unstructured":"Eysenbach B, Gupta A, Levine S, Finn C (2019) Diversity is all you need: Learning skills without a reward function. In: ICLR"},{"key":"7485_CR29","unstructured":"Sharma A, Gu S, Levine S, Kumar V (2020) Dynamics-aware unsupervised discovery of skills. In: ICLR"},{"key":"7485_CR30","unstructured":"Achiam J, Sastry S (2018) Valor: Value-aware learning of reward-agnostic skills. In: NeurIPS"},{"key":"7485_CR31","unstructured":"Pertsch K, Lee Y, Lim JJ (2020) Accelerating reinforcement learning with learned skill priors. In: Conference on Robot Learning, CoRL"},{"key":"7485_CR32","doi-asserted-by":"publisher","first-page":"38600","DOI":"10.52202\/068431-2797","volume":"35","author":"M Xu","year":"2022","unstructured":"Xu M, Veloso M, Song S (2022) Aspire: Adaptive skill priors for reinforcement learning. Adv Neural Inf Process Syst 35:38600\u201338613","journal-title":"Adv Neural Inf Process Syst"},{"key":"7485_CR33","unstructured":"Sharma Aea (2023) Reskill: Skill abstractions with normalizing flows for compositional control. arXiv preprint arXiv:2302.03126"},{"key":"7485_CR34","doi-asserted-by":"crossref","unstructured":"Sutton RS, Precup D, Singh S (1999) Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artif Intell","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"7485_CR35","doi-asserted-by":"crossref","unstructured":"Bacon P-L, Harb J, Precup D (2017) The option-critic architecture. In: Proceedings of the AAAI conference on artificial intelligence, p 31","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"7485_CR36","unstructured":"Shankar K, Gupta A (2020) Discovering options via meta-learned goal spaces. In: Conference on Learning Representations, ICLR"},{"key":"7485_CR37","unstructured":"Harutyunyan A, Dabney W, Borsa D, Heess N, Munos R, Precup D (2019) The termination critic. arXiv preprint arXiv:1902.09996"},{"key":"7485_CR38","unstructured":"Jiang Y, Gupta A, Finn C (2022) Skill discovery via information bottlenecks. In: Conference on Learning Representations, ICLR"},{"key":"7485_CR39","unstructured":"Fu J, Kumar A, Nachum O, Tucker G, Levine S (2021) D4rl: Datasets for deep data-driven reinforcement learning. In: International Conference on Learning Representations, ICLR"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07485-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-026-07485-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07485-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T07:46:23Z","timestamp":1792827983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-026-07485-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":39,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["7485"],"URL":"https:\/\/doi.org\/10.1007\/s10489-026-07485-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]},"assertion":[{"value":"12 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflicts of Interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"444"}}