{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T15:07:28Z","timestamp":1774105648475,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2017,2,27]],"date-time":"2017-02-27T00:00:00Z","timestamp":1488153600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1007\/s13042-017-0639-y","type":"journal-article","created":{"date-parts":[[2017,2,27]],"date-time":"2017-02-27T11:12:37Z","timestamp":1488193957000},"page":"1169-1179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Control the population of free viruses in nonlinear uncertain HIV system using Q-learning"],"prefix":"10.1007","volume":"9","author":[{"given":"Hossein","family":"Gholizade-Narm","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amin","family":"Noori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,2,27]]},"reference":[{"key":"639_CR1","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1038\/nsmb.1861","volume":"17","author":"X Jiang","year":"2010","unstructured":"Jiang X, Burke V, Totrov M, Williams C, Cardozo T, Gomy MK, Pazner SZ, Kong XP (2010) Conserved structural elements in the V3 crown of HIV-1 gp120. Nat Struct Mol Biol 17:955\u2013961","journal-title":"Nat Struct Mol Biol"},{"key":"639_CR2","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1006\/jtbi.1996.0253","volume":"185","author":"L Wein","year":"1997","unstructured":"Wein L, Zenio S, Nowak M (1997) Dynamics multidrug therapies for HIV: a theoretic approach. J Theor Biol 185:15\u201329","journal-title":"J Theor Biol"},{"issue":"3","key":"639_CR3","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/TBME.2004.840463","volume":"52","author":"S Ge","year":"2005","unstructured":"Ge S, Tian Z, Lee T (2005) Nonlinear control of a dynamic model of HIV-1. IEEE Trans Biomed Eng 52(3):353\u2013361","journal-title":"IEEE Trans Biomed Eng"},{"issue":"7","key":"639_CR4","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1109\/10.930900","volume":"48","author":"ME Brandt","year":"2001","unstructured":"Brandt ME, Chen G (2001) Feedback control of a biodynamical model of HIV-1. IEEE Trans Biomed Eng 48(7):754\u2013759","journal-title":"IEEE Trans Biomed Eng"},{"key":"639_CR5","doi-asserted-by":"crossref","unstructured":"Ledzewicz U, Schattler H (2002) On optimal controls for a general mathematical model for chemotherapy of HIV. In: Proceedings of the American control conference, pp\u00a03454\u20133459","DOI":"10.1109\/ACC.2002.1024461"},{"key":"639_CR6","doi-asserted-by":"crossref","unstructured":"Ouattara DA (2005) Mathematical analysis of the HIV-1 infection: parameter estimation, therapies effectiveness and therapeutical failures. The 27th annual conference on engineering in medicine and biology, September 1\u20134, 2005, Shanghai, China","DOI":"10.1109\/IEMBS.2005.1616541"},{"key":"639_CR7","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1007\/s002850050076","volume":"35","author":"D Kirschner","year":"1997","unstructured":"Kirschner D, Lenhart S, Serbin S (1997) Optimal control of the chemotherapy of HIV. J Math Biol 35:775\u2013792","journal-title":"J Math Biol"},{"key":"639_CR8","unstructured":"Kubiak S, Lehr H, Levy R, Moeller T, Parker A, Swim E (2001) Modeling control of HIV infection through structured treatment interruptions with recommendations for experimental protocol. CRSC Technical Report (CRSCTR01-27)"},{"key":"639_CR9","doi-asserted-by":"crossref","unstructured":"Kutch JJ, Gurfil P (2002) Optimal control of HIV infection with a continuously-mutating viral population. In: Proceedings of American control conference, pp\u00a04033\u20134038","DOI":"10.1109\/ACC.2002.1024560"},{"issue":"3","key":"639_CR10","first-page":"282","volume":"1","author":"H Shim","year":"2003","unstructured":"H Shim, SJ Han, CC Chung, SW Nam, JH Seo (2003) Optimal scheduling of drug treatment for HIV infection: continues dose control and receding horizon control. Int J Control Autom Syst 1(3):282\u2013288","journal-title":"Int J Control Autom Syst"},{"key":"639_CR11","doi-asserted-by":"crossref","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell:237\u2013285","DOI":"10.1613\/jair.301"},{"key":"639_CR12","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"639_CR13","volume-title":"Dynamic programming and optimal control","author":"DP Bertsekas","year":"2007","unstructured":"Bertsekas DP (2007) Dynamic programming and optimal control, 3 ed. Athena Scientic, Belmont"},{"key":"639_CR14","unstructured":"Shoham Y, Powers R, Grenager T (2003) Multi-agent reinforcement learning: a critical survey. Web Manuscript"},{"key":"639_CR15","volume-title":"Stochastic learning and optimization: a sensitivity-based approach","author":"XR Cao","year":"2007","unstructured":"Cao XR (2007) Stochastic learning and optimization: a sensitivity-based approach. Springer, Berlin"},{"key":"639_CR16","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume-title":"Approximate dynamic programming: solving the curses of dimensionality","author":"WB Powell","year":"2007","unstructured":"Powell WB (2007) Approximate dynamic programming: solving the curses of dimensionality. Wiley, New York"},{"key":"639_CR17","volume-title":"Simulation-based algorithms for markov decision processes","author":"HS Chang","year":"2008","unstructured":"Chang HS, Fu MC, Hu J, Marcus SI (2008) Simulation-based algorithms for markov decision processes. Springer, Berlin"},{"key":"639_CR18","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor ME, Stone P (2009) Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res 10:1633\u20131685","journal-title":"J Mach Learn Res"},{"key":"639_CR19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","volume-title":"Reinforcement learning state-of-the-art","author":"MO Wiering","year":"2012","unstructured":"Wiering MO, Otterlo MV (2012) Reinforcement learning state-of-the-art. Springer, Berlin"},{"key":"639_CR20","unstructured":"Faust A (2012) Reinforcement learning as a motion planner\u2014a survey. Technical report, University of New Mexico, Department of Computer Science, 2012. Online: http:\/\/www.cs.unm.edu\/~pdevineni\/papers\/Faust.pdf"},{"key":"639_CR21","doi-asserted-by":"crossref","unstructured":"Kober J, Bagnell JA, Peters J (2013) Reinforcement learning in robotics: a survey. Int J Robot Res","DOI":"10.1177\/0278364913495721"},{"key":"639_CR22","doi-asserted-by":"crossref","unstructured":"Liu DR, Li HL, Wang D (2015) Feature selection and feature learning for high-dimensional batch reinforcement learning: a survey. Int J Autom Comp:1\u201314","DOI":"10.1007\/s11633-015-0893-y"},{"key":"639_CR23","first-page":"1437","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda J, Fernando F (2015) A comprehensive survey on safe reinforcement learning. J Mach Learn Res 16:1437\u20131480","journal-title":"J Mach Learn Res"},{"key":"639_CR24","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.bspc.2010.08.006","volume":"6","author":"JM Orellana","year":"2011","unstructured":"Orellana JM (2011) Optimal drug scheduling for HIV therapy efficiency improvement. Biomed Signal Process Control 6:379\u2013386","journal-title":"Biomed Signal Process Control"},{"key":"639_CR25","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.bspc.2012.06.002","volume":"8","author":"V Costanza","year":"2013","unstructured":"Costanza V, Rivadeneira PS, Biafore FL, D\u2019Attellis CE (2013) Optimizing thymic recovery in HIV patients through multidrug therapies. Biomed Signal Process Control 8:90\u201397","journal-title":"Biomed Signal Process Control"},{"key":"639_CR26","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.biosystems.2014.03.006","volume":"119","author":"FB Agusto","year":"2014","unstructured":"Agusto FB, Adekunle AI (2014) Optimal control of a two-strain tuberculosis-HIV\/AIDS co-infection model. Biosystems 119:20\u201344","journal-title":"Biosystems"},{"key":"639_CR27","first-page":"119","volume":"115","author":"BZ Guo","year":"2012","unstructured":"Guo BZ, Sun B (2012) Dynamic programming approach to the numerical solution of optimal control with paradigm by a mathematical model for drug therapies of HIV\/AIDS. Optim Eng 115:119\u2013136","journal-title":"Optim Eng"},{"key":"639_CR28","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.artmed.2009.05.002","volume":"47","author":"D Wang","year":"2009","unstructured":"Wang D et al (2009) A comparison of three computational modelling methods for the prediction of virological response to combination HIV therapy. Artif Intell Med 47:63\u201374","journal-title":"Artif Intell Med"},{"key":"639_CR29","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.bspc.2013.11.005","volume":"10","author":"E Abharian","year":"2014","unstructured":"Abharian E, Sarabi SZ, Yomi M (2014) Optimal sigmoid nonlinear stochastic control of HIV-1 infection based on bacteria foraging optimization method. Biomed Signal Process Control 10:184\u2013191","journal-title":"Biomed Signal Process Control"},{"key":"639_CR30","unstructured":"Parbhoo S (2014) A reinforcement learning design for HIV clinical trials. PhD Diss"},{"key":"639_CR31","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/j.neunet.2005.06.020","volume":"18","author":"E Gaweda","year":"2005","unstructured":"Gaweda E et al (2005) Individualization of pharmacological anemia management using reinforcement learning. Neural Netw 18:826\u2013834","journal-title":"Neural Netw"},{"key":"639_CR32","unstructured":"Noori A, Naghibi Sistani MB, Pariz N (2011) Hepatitis B virus infection control using reinforcement learning, presented at the ICEEE"},{"key":"639_CR33","first-page":"2009","volume":"5","author":"S Yassini","year":"2009","unstructured":"Yassini S, Naghibi-Sistani MB (2009) Agent-based simulation for blood glucose control in diabetic patients. Int J Appl Sci Eng Technol 5:2009","journal-title":"Int J Appl Sci Eng Technol"},{"key":"639_CR34","unstructured":"Wong WC, Lee JH (2008) A reinforcement learning based scheme for adaptive optimal control of linear stochastic systems. American Control Conference, Seatle, Washington, USA, June 2008"},{"key":"639_CR35","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/S0025-5564(00)00069-9","volume":"170","author":"RW Kamina","year":"2001","unstructured":"Kamina RW, Makuch, H Zhao (2001) A stochastic modeling of early HIV-1 population dynamics. J Math Biosci 170:187\u2013198","journal-title":"J Math Biosci"},{"key":"639_CR36","doi-asserted-by":"crossref","unstructured":"Alazabi FA, Zohdy MA (2012) Nonlinear uncertain HIV-1 model controller by using control Lyapunov function. Int J Mod Nonlinear Theory Appl:33\u201339","DOI":"10.4236\/ijmnta.2012.12004"},{"key":"639_CR37","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1002\/bies.10196","volume":"24","author":"D Wodarz","year":"2002","unstructured":"Wodarz D, Nowak MA (2002) Mathematical models of HIV pathogenesis and treatment. Bioessays 24:1178\u20131187","journal-title":"Bioessays"},{"key":"639_CR38","unstructured":"Ortega H, Martin-Landrove M (1999) A model for continuously mutant HIV-1. In: Proceedings of 22nd annual EMBS international conference, Chicago, pp 1917\u20131920, 2000"},{"issue":"1","key":"639_CR39","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1137\/S0036144598335107","volume":"41","author":"AS Perelson","year":"1999","unstructured":"Perelson AS, Nelson PW (1999) Mathematical analysis of HIV-1 dynamics in vivo. SIAM Rev 41(1):3\u201344","journal-title":"SIAM Rev"},{"issue":"25","key":"639_CR40","doi-asserted-by":"crossref","first-page":"14464","DOI":"10.1073\/pnas.96.25.14464","volume":"96","author":"D Wodarz","year":"1999","unstructured":"Wodarz D, Nowak MA (1999) Specific therapy regimes could lead to long-term immunological control of HIV. Proc Natl Acad Sci 96(25):14464\u201314469","journal-title":"Proc Natl Acad Sci"},{"key":"639_CR41","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1006\/jtbi.2001.2426","volume":"213","author":"D Wodarz","year":"2001","unstructured":"Wodarz D (2001) Helper-dependent vs. helper-independent CTL responses in HIV infection: implications for drug therapy and resistance. J Theor Biol 213:447\u2013459","journal-title":"J Theor Biol"},{"issue":"11","key":"639_CR42","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1109\/TBME.2003.818465","volume":"50","author":"M Jeffrey","year":"2003","unstructured":"Jeffrey M, Xia X, Craig I (2003) When to initiate HIV therapy: a control theoretic approach. IEEE Trans Biomed Eng 50(11):1213\u20131220","journal-title":"IEEE Trans Biomed Eng"},{"key":"639_CR43","first-page":"1989","volume-title":"Modeling the interaction of the immune system with HIV, Castillo\u2013Chavez, mathematical and statistical approaches to AIDS epidemiology, (Lect. Notes in Biomath 83, pp.350\u2013370)","author":"AS Perelson","year":"1989","unstructured":"Perelson AS (1989) Modeling the interaction of the immune system with HIV, Castillo\u2013Chavez, mathematical and statistical approaches to AIDS epidemiology, (Lect. Notes in Biomath 83, pp.\u00a0350\u2013370). Springer, New York, p\u00a01989"},{"key":"639_CR44","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/0025-5564(93)90043-A","volume":"114","author":"A Perelson","year":"1993","unstructured":"Perelson A, Kirschner D, DeBoer R (1993) The dynamics of HIV infection of CD4 T-cells. Math Biosci 114:125","journal-title":"Math Biosci"},{"key":"639_CR45","unstructured":"Watkins C (1998) Learning from delayed rewards. Ph. D. Dissertation Cambridge University"},{"key":"639_CR46","volume-title":"Linear system theory and design","author":"CT Chen","year":"1995","unstructured":"Chen CT (1995) Linear system theory and design, 3rd edition. Oxford University Press, Oxford","edition":"3"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13042-017-0639-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-017-0639-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-017-0639-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,19]],"date-time":"2019-09-19T04:01:35Z","timestamp":1568865695000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13042-017-0639-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,27]]},"references-count":46,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["639"],"URL":"https:\/\/doi.org\/10.1007\/s13042-017-0639-y","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,27]]}}}