{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:04:16Z","timestamp":1743141856212,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031714696"},{"type":"electronic","value":"9783031714702"}],"license":[{"start":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T00:00:00Z","timestamp":1731456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T00:00:00Z","timestamp":1731456000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-71470-2_10","type":"book-chapter","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T17:10:01Z","timestamp":1731431401000},"page":"114-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale Data Reconstruction Based Policy Optimization Algorithm for\u00a0Skill Learning"],"prefix":"10.1007","author":[{"given":"Haoke","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yiyong","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Chuanfu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanjie","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,13]]},"reference":[{"issue":"1","key":"10_CR1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s42256-021-00433-9","volume":"4","author":"M Eppe","year":"2022","unstructured":"Eppe, M., Gumbsch, C., Kerzel, M., Nguyen, P.D., Butz, M.V., Wermter, S.: Intelligent problem-solving as integrated hierarchical reinforcement learning. Nature Mach. Intell. 4(1), 11\u201320 (2022)","journal-title":"Nature Mach. Intell."},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning. nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"10_CR3","unstructured":"Abeyruwan, S.W., et al.: i-sim2real: reinforcement learning of robotic policies in tight human-robot interaction loops. In: Conference on Robot Learning, pp. 212\u2013224. PMLR (2023)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, P., Wang, Y.: Autonomous target tracking of multi-uav: a two-stage deep reinforcement learning approach with expert experience. Appl. Soft Comput., p. 110604 (2023)","DOI":"10.1016\/j.asoc.2023.110604"},{"issue":"30","key":"10_CR5","doi-asserted-by":"publisher","first-page":"22563","DOI":"10.1007\/s00521-023-08845-x","volume":"35","author":"AC Kapoutsis","year":"2023","unstructured":"Kapoutsis, A.C., Koutras, D.I., Korkas, C.D., Kosmatopoulos, E.B.: Acre: actor-critic with reward-preserving exploration. Neural Comput. Appl. 35(30), 22563\u201322576 (2023)","journal-title":"Neural Comput. Appl."},{"key":"10_CR6","unstructured":"Pertsch, K., Lee, Y., Lim, J.: Accelerating reinforcement learning with learned skill priors. In: Conference on Robot Learning, pp. 188\u2013204. PMLR (2021)"},{"key":"10_CR7","unstructured":"Chane-Sane, E., Schmid, C., Laptev, I.: Goal-conditioned reinforcement learning with imagined subgoals. In: International Conference on Machine Learning, pp. 1430\u20131440. PMLR (2021)"},{"key":"10_CR8","unstructured":"Wulfmeier, M., et\u00a0al.: Data-efficient hindsight off-policy option learning. In: International Conference on Machine Learning, pp. 11340\u201311350. PMLR (2021)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, F., Lim, S.N., Belongie, S., Weinberger, K.Q.: On feature normalization and data augmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12383\u201312392 (2021)","DOI":"10.1109\/CVPR46437.2021.01220"},{"key":"10_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108969","volume":"123","author":"L Zhang","year":"2022","unstructured":"Zhang, L., Zhou, G., Lu, C., Chen, A., Wang, Y., Li, L., Cai, W.: Mmdgan: a fusion data augmentation method for tomato-leaf disease identification. Appl. Soft Comput. 123, 108969 (2022)","journal-title":"Appl. Soft Comput."},{"issue":"6","key":"10_CR11","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/S1364-6613(99)01327-3","volume":"3","author":"S Schaal","year":"1999","unstructured":"Schaal, S.: Is imitation learning the route to humanoid robots? Trends Cogn. Sci. 3(6), 233\u2013242 (1999)","journal-title":"Trends Cogn. Sci."},{"issue":"11","key":"10_CR12","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Gradient-based learning applied to document recognition","year":"1998","unstructured":"Gradient-based learning applied to document recognition: Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"issue":"6","key":"10_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: Stargan: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789\u20138797 (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: Stargan v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8188\u20138197 (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Gong, C., Wang, D., Li, M., Chandra, V., Liu, Q.: Keepaugment: a simple information-preserving data augmentation approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1055\u20131064 (2021)","DOI":"10.1109\/CVPR46437.2021.00111"},{"key":"10_CR20","first-page":"310","volume":"35","author":"JY Ma","year":"2022","unstructured":"Ma, J.Y., Yan, J., Jayaraman, D., Bastani, O.: Offline goal-conditioned reinforcement learning via $$ f $$-advantage regression. Adv. Neural. Inf. Process. Syst. 35, 310\u2013323 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"10_CR21","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1109\/LRA.2021.3140127","volume":"7","author":"N Lin","year":"2022","unstructured":"Lin, N., et al.: Manipulation planning from demonstration via goal-conditioned prior action primitive decomposition and alignment. IEEE Robot. Automation Lett. 7(2), 1387\u20131394 (2022)","journal-title":"IEEE Robot. Automation Lett."},{"issue":"2","key":"10_CR22","doi-asserted-by":"publisher","first-page":"2883","DOI":"10.1109\/LRA.2022.3143198","volume":"7","author":"L Wang","year":"2022","unstructured":"Wang, L., Meng, X., Xiang, Y., Fox, D.: Hierarchical policies for cluttered-scene grasping with latent plans. IEEE Robot. Automation Lett. 7(2), 2883\u20132890 (2022). https:\/\/doi.org\/10.1109\/LRA.2022.3143198","journal-title":"IEEE Robot. Automation Lett."},{"key":"10_CR23","unstructured":"Rosete-Beas, E., Mees, O., Kalweit, G., Boedecker, J., Burgard, W.: Latent plans for task-agnostic offline reinforcement learning. In: Conference on Robot Learning, pp. 1838\u20131849. PMLR (2023)"},{"key":"10_CR24","unstructured":"Gupta, A., Kumar, V., Lynch, C., Levine, S., Hausman, K.: Relay policy learning: solving long-horizon tasks via imitation and reinforcement learning. In: Conference on Robot Learning, pp. 1025\u20131037. PMLR (2020)"},{"key":"10_CR25","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4rl: datasets for deep data-driven reinforcement learning (2020)"},{"key":"10_CR26","unstructured":"Pertsch, K., Lee, Y., Wu, Y., Lim, J.J.: Guided reinforcement learning with learned skills. arXiv preprint arXiv:2107.10253 (2021)"},{"key":"10_CR27","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"}],"container-title":["Lecture Notes in Computer Science","Wireless Artificial Intelligent Computing Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-71470-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T18:08:07Z","timestamp":1731434887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-71470-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,13]]},"ISBN":["9783031714696","9783031714702"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-71470-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,13]]},"assertion":[{"value":"13 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Wireless Artificial Intelligent Computing Systems and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wasa2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wasa-conference.org\/WASA2024\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}