{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T20:52:32Z","timestamp":1760043152508,"version":"3.37.3"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100010418","name":"institute for information and communications technology promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s11370-021-00409-z","type":"journal-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T11:03:21Z","timestamp":1646132601000},"page":"203-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep latent-space sequential skill chaining from incomplete demonstrations"],"prefix":"10.1007","volume":"15","author":[{"given":"Minjae","family":"Kang","sequence":"first","affiliation":[]},{"given":"Songhwai","family":"Oh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,1]]},"reference":[{"key":"409_CR1","doi-asserted-by":"crossref","unstructured":"Bacon PL, Harb J, Precup D (2017) The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"409_CR2","unstructured":"Bagaria A, Konidaris G (2019) Option discovery using deep skill chaining. In: International Conference on Learning Representations"},{"key":"409_CR3","unstructured":"Fujimoto S, van Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods. In: Proceedings of the 35th International Conference on Machine Learning, ICML, pp 1582\u20131591"},{"key":"409_CR4","unstructured":"Haarnoja T, Tang H, Abbeel P, et\u00a0al (2017) Reinforcement learning with deep energy-based policies. In: International Conference on Machine Learning, PMLR, pp 1352\u20131361"},{"key":"409_CR5","unstructured":"Haarnoja T, Zhou A, Abbeel P, et\u00a0al (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning, ICML, pp 1856\u20131865"},{"key":"409_CR6","unstructured":"Ho J, Ermon S (2016) Generative adversarial imitation learning. arxiv:1606.03476"},{"key":"409_CR7","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arxiv:1312.6114"},{"key":"409_CR8","first-page":"1015","volume":"22","author":"G Konidaris","year":"2009","unstructured":"Konidaris G, Barto A (2009) Skill discovery in continuous reinforcement learning domains using skill chaining. Adv Neural Inf Process Syst 22:1015\u20131023","journal-title":"Adv Neural Inf Process Syst"},{"key":"409_CR9","doi-asserted-by":"crossref","unstructured":"Lee G, Kim D, Oh W, et\u00a0al (2020) Mixgail: Autonomous driving using demonstrations with mixed qualities. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp 5425\u20135430","DOI":"10.1109\/IROS45743.2020.9341104"},{"key":"409_CR10","unstructured":"Lee K, Choi S, Oh S (2018) Maximum causal tsallis entropy imitation learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp 4408\u20134418"},{"key":"409_CR11","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et\u00a0al (2015) Continuous control with deep reinforcement learning. arxiv:1509.0297"},{"key":"409_CR12","unstructured":"Nachum O, Gu S, Lee H, et\u00a0al (2018) Data-efficient hierarchical reinforcement learning. arxiv:1805.08296"},{"key":"409_CR13","unstructured":"Ng AY, Russell SJ (2000) Algorithms for inverse reinforcement learning. In: Proc. of the International Conference on Machine Learning"},{"key":"409_CR14","first-page":"4026","volume":"26","author":"I Osband","year":"2016","unstructured":"Osband I, Blundell C, Pritzel A et al (2016) Deep exploration via bootstrapped DQN. Adv Neural Inf Process Syst 26:4026\u20134034","journal-title":"Adv Neural Inf Process Syst"},{"key":"409_CR15","doi-asserted-by":"crossref","unstructured":"Pan Y, Cheng CA, Saigol K, et\u00a0al (2017) Agile autonomous driving using end-to-end deep imitation learning. arxiv:1709.0717","DOI":"10.15607\/RSS.2018.XIV.056"},{"key":"409_CR16","unstructured":"Peng XB, Kanazawa A, Toyer S, et\u00a0al (2018) Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow. arxiv:1810.00821"},{"key":"409_CR17","unstructured":"Peng XB, Coumans E, Zhang T, et\u00a0al (2020) Learning agile robotic locomotion skills by imitating animals. Robotics: Science and Systems (RSS)"},{"key":"409_CR18","unstructured":"Pomerleau DA (1989) Alvinn: An autonomous land vehicle in a neural network. In: Advances in neural information processing systems"},{"key":"409_CR19","doi-asserted-by":"crossref","unstructured":"Ratliff N, Bagnell JA, Srinivasa SS (2007) Imitation learning for locomotion and manipulation. In: 2007 7th IEEE-RAS International Conference on Humanoid Robots, IEEE, pp 392\u2013397","DOI":"10.1109\/ICHR.2007.4813899"},{"key":"409_CR20","unstructured":"Schulman J, Wolski F, Dhariwal P, et\u00a0al (2017) Proximal policy optimization algorithms. CoRR"},{"key":"409_CR21","unstructured":"Vezhnevets AS, Osindero S, Schaul T, et\u00a0al (2017) Feudal networks for hierarchical reinforcement learning. In: International Conference on Machine Learning, PMLR, pp 3540\u20133549"},{"key":"409_CR22","unstructured":"Xie F, Chowdhury A, Kaluza M, et\u00a0al (2020) Deep imitation learning for bimanual robotic manipulation. arxiv:2010.0513"},{"key":"409_CR23","doi-asserted-by":"crossref","unstructured":"Zhang T, McCarthy Z, Jow O, et\u00a0al (2018) Deep imitation learning for complex manipulation tasks from virtual reality teleoperation. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 5628\u20135635","DOI":"10.1109\/ICRA.2018.8461249"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-021-00409-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-021-00409-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-021-00409-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T04:26:27Z","timestamp":1674879987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-021-00409-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["409"],"URL":"https:\/\/doi.org\/10.1007\/s11370-021-00409-z","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"type":"print","value":"1861-2776"},{"type":"electronic","value":"1861-2784"}],"subject":[],"published":{"date-parts":[[2022,3,1]]},"assertion":[{"value":"22 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}