{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:14:01Z","timestamp":1740158041929,"version":"3.37.3"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T00:00:00Z","timestamp":1542412800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702055"],"award-info":[{"award-number":["61702055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education","award":["93K172014K04"],"award-info":[{"award-number":["93K172014K04"]}]},{"name":"Program of Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1007\/s12652-018-1133-4","type":"journal-article","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T07:53:10Z","timestamp":1542441190000},"page":"527-537","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Online model-learning algorithm from samples and trajectories"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-6952","authenticated-orcid":false,"given":"Shan","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiming","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaijian","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengrong","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,17]]},"reference":[{"key":"1133_CR1","volume-title":"Reinforcement Learning and dynamic programming using function approximators","author":"L Busoniu","year":"2010","unstructured":"Busoniu L. Babu\u0161ka R, Schutter BD et al (2010) Reinforcement Learning and dynamic programming using function approximators. CRC Press, New York"},{"key":"1133_CR2","doi-asserted-by":"crossref","unstructured":"Grondman I, Busoniu L, Babuska R (2012a) Model learning actor-critic algorithms: performance evaluation in a motion control task. In: Proceedings of IEEE conference on decision and control, pp\u00a05272\u20135277","DOI":"10.1109\/CDC.2012.6426427"},{"key":"1133_CR3","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TSMCB.2011.2170565","volume":"42","author":"I Grondman","year":"2012","unstructured":"Grondman I, Vaandrager M, Busoniu L et al (2012b) Efficient model learning methods for actor\u2013critic control systems. IEEE Trans Syst Man Cybern 42:591\u2013602","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"1133_CR4","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1109\/LRA.2017.2720851","volume":"2","author":"J Hwangbo","year":"2017","unstructured":"Hwangbo J, Sa I, Siegwart R et al (2017) Control of a quadrotor with reinforcement learning. IEEE Robot Auto Lett 2:2096\u20132103","journal-title":"IEEE Robot Auto Lett"},{"key":"1133_CR5","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/tmc.2017.2744620","volume":"17","author":"AM Koushik","year":"2018","unstructured":"Koushik AM, Hu F, Kumar S (2018) Intelligent spectrum management based on transfer actor-critic learning for rateless transmissions in cognitive radio networks. IEEE Trans Mob Comput 17:1204\u20131215. https:\/\/doi.org\/10.1109\/tmc.2017.2744620","journal-title":"IEEE Trans Mob Comput"},{"key":"1133_CR6","doi-asserted-by":"crossref","unstructured":"Lample G, Chaplot DS (2017) Playing fps games with deep reinforcement learning. In: Proceedings of association for the advance of artificial intelligence, pp\u00a02140\u20132146","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"1133_CR7","doi-asserted-by":"publisher","unstructured":"Li L, Li D, Song T (2017) Sustainable \u21132-regularized actor-critic based on recursive least-squares temporal difference learning. In: Proceedings of international conference on systems, man, and cybernetics, pp\u00a01886\u20131891. https:\/\/doi.org\/10.1109\/smc.2017.8122892","DOI":"10.1109\/smc.2017.8122892"},{"key":"1133_CR8","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1038\/nature14540","volume":"7553","author":"ML Littman","year":"2015","unstructured":"Littman ML (2015) Reinforcement learning improves behaviour from evaluative feedback. Nature 7553:445\u2013451. https:\/\/doi.org\/10.1038\/nature14540","journal-title":"Nature"},{"key":"1133_CR9","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/bf00993104","volume":"1","author":"AW Moore","year":"1993","unstructured":"Moore AW, Atkeson CG (1993) Prioritized sweeping: Reinforcement learning with less data and less real time. Mach Learn 1:103\u2013130. https:\/\/doi.org\/10.1007\/bf00993104","journal-title":"Mach Learn"},{"key":"1133_CR10","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1177\/105971239300100403","volume":"1","author":"J Peng","year":"1993","unstructured":"Peng J, Williams RJ (1993) Efficient learning and planning within the Dyna framework. Adapt Behav 1:437\u2013454. https:\/\/doi.org\/10.1177\/105971239300100403","journal-title":"Adapt Behav"},{"key":"1133_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0777-4","author":"SM Sombolestan","year":"2018","unstructured":"Sombolestan SM, Rasooli A, Khodaygan S (2018) Optimal path-planning for mobile robots to find a hidden target in an unknown environment based on machine learning. J Ambient Intell Human Comput. https:\/\/doi.org\/10.1007\/s12652-018-0777-4","journal-title":"J Ambient Intell Human Comput"},{"key":"1133_CR12","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/B978-1-55860-141-3.50030-4","volume-title":"Machine Learning Proceedings 1990","author":"Richard S. Sutton","year":"1990","unstructured":"Sutton RS (1990) Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceedings of international conference on machine learning, pp.\u00a0216\u2013224"},{"key":"1133_CR13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Introduction to reinforcement learning. MIT press, Cambridge"},{"key":"1133_CR14","unstructured":"Sutton RS, Szepesv\u00e1ri C, Geramfard A et al (2008) Dyna-style planning with linear function approximation and prioritized sweeping. In: Proceedings of uncertainty in artificial intelligence, pp\u00a01\u20139"},{"key":"1133_CR15","unstructured":"Tagorti M, Scherer B (2015) On the rate of the convergence and error bounds for LSTD(\u03bb). In: Proceedings of international conference on machine learning, pp\u00a0528\u2013536"},{"key":"1133_CR16","doi-asserted-by":"crossref","unstructured":"Venkatraman A, Hebert M, Bagnell JA (2015) Improving multi-step prediction of learned time series models. In: Proceedings of association for the advance of artificial intelligence, pp\u00a03024\u20133030","DOI":"10.1609\/aaai.v29i1.9590"},{"key":"1133_CR17","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1007\/978-3-319-50115-4_61","volume-title":"Springer Proceedings in Advanced Robotics","author":"Arun Venkatraman","year":"2017","unstructured":"Venkatraman A, Capobianco R, Pinto L et al (2016) Improved learning of dynamics models for control. In: Proceedings of advanced robotics, pp\u00a0703\u2013713. https:\/\/doi.org\/10.1007\/978-3-319-50115-4_61"},{"key":"1133_CR18","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1109\/TNNLS.2015.2464080","volume":"27","author":"Q Wei","year":"2016","unstructured":"Wei Q, Song R, Yan P (2016) Data-driven zero-sum neuro-optimal control for a class of continuous-time unknown nonlinear systems with disturbance using ADP. IEEE Trans Neural Netw Learn Syst 27:444\u2013458. https:\/\/doi.org\/10.1109\/TNNLS.2015.2464080","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1133_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0682-x","author":"Z Zang","year":"2018","unstructured":"Zang Z, Li Z, Dan Z et al (2018) Improving selection strategies in zeroth-level classifier systems based on average reward reinforcement learning. J Ambient Intell Humaniz Comput. https:\/\/doi.org\/10.1007\/s12652-018-0682-x","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"1133_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-017-6222-6","author":"S Zhong","year":"2018","unstructured":"Zhong S, Liu Q, Zhang Z et al (2018) Efficient reinforcement learning in continuous state and action spaces with Dyna and policy approximation. Front Comput Sci. https:\/\/doi.org\/10.1007\/s11704-017-6222-6","journal-title":"Front Comput Sci"},{"key":"1133_CR21","doi-asserted-by":"crossref","unstructured":"Zhu Y, Mottaghi R, Kolve E et al (2017) Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: Proceedings of IEEE international conference on robotics and automation, pp\u00a03357\u20133364","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-018-1133-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12652-018-1133-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-018-1133-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T06:10:02Z","timestamp":1662444602000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12652-018-1133-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,17]]},"references-count":21,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["1133"],"URL":"https:\/\/doi.org\/10.1007\/s12652-018-1133-4","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"type":"print","value":"1868-5137"},{"type":"electronic","value":"1868-5145"}],"subject":[],"published":{"date-parts":[[2018,11,17]]},"assertion":[{"value":"8 June 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}