{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T04:59:27Z","timestamp":1771477167861,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,5,11]],"date-time":"2020-05-11T00:00:00Z","timestamp":1589155200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,11]],"date-time":"2020-05-11T00:00:00Z","timestamp":1589155200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["SMeL"],"award-info":[{"award-number":["SMeL"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["2724"],"award-info":[{"award-number":["2724"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"crossref","award":["ASTERIQS"],"award-info":[{"award-number":["ASTERIQS"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["QIA"],"award-info":[{"award-number":["QIA"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Max-Planck-Gesellschaft"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Quantum Mach. Intell."],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s42484-020-00016-8","type":"journal-article","created":{"date-parts":[[2020,5,11]],"date-time":"2020-05-11T07:02:51Z","timestamp":1589180571000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["A reinforcement learning approach for quantum state engineering"],"prefix":"10.1007","volume":"2","author":[{"given":"Jelena","family":"Mackeprang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Durga B. Rao","family":"Dasari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00f6rg","family":"Wrachtrup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,11]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","first-page":"183","DOI":"10.22331\/q-2019-09-02-183","volume":"3","author":"P Andreasson","year":"2019","unstructured":"Andreasson P, Johansson J, Liljestrand S, Granath M (2019) Quantum error correction for the toric code using deep reinforcement learning. Quantum 3:183. https:\/\/doi.org\/10.22331\/q-2019-09-02-183","journal-title":"Quantum"},{"key":"16_CR2","doi-asserted-by":"publisher","first-page":"022,307","DOI":"10.1103\/PhysRevA.100.022307","volume":"100","author":"DD Bhaktavatsala Rao","year":"2019","unstructured":"Bhaktavatsala Rao DD, Yang S, Jesenski S, Tekin E, Kaiser F, Wrachtrup J (2019) Observation of nonclassical measurement statistics induced by a coherent spin environment. Phys Rev A 100:022,307. https:\/\/doi.org\/10.1103\/PhysRevA.100.022307","journal-title":"Phys Rev A"},{"key":"16_CR3","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1038\/srep00400","volume":"2","author":"HJ Briegel","year":"2012","unstructured":"Briegel HJ, De las Cuevas G (2012) Projective simulation for artificial intelligence. Sci Report 2:400. https:\/\/doi.org\/10.1038\/srep00400. https:\/\/www.nature.com\/articles\/srep00400","journal-title":"Sci Report"},{"key":"16_CR4","doi-asserted-by":"publisher","first-page":"224,305","DOI":"10.1103\/PhysRevB.98.224305","volume":"98","author":"M Bukov","year":"2018","unstructured":"Bukov M (2018) Reinforcement learning for autonomous preparation of Floquet-engineered states: Inverting the quantum Kapitza oscillator. Phys Rev B 98:224,305. https:\/\/doi.org\/10.1103\/PhysRevB.98.224305","journal-title":"Phys Rev B"},{"issue":"3","key":"16_CR5","doi-asserted-by":"publisher","first-page":"031,086","DOI":"10.1103\/PhysRevX.8.031086","volume":"8","author":"M Bukov","year":"2018","unstructured":"Bukov M, Day AG, Sels D, Weinberg P, Polkovnikov A, Mehta P (2018) Reinforcement learning in different phases of quantum control. Phys Rev X 8(3):031,086. https:\/\/doi.org\/10.1103\/PhysRevX.8.031086","journal-title":"Phys Rev X"},{"issue":"5","key":"16_CR6","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/TNNLS.2013.2283574","volume":"25","author":"C Chen","year":"2014","unstructured":"Chen C, Dong D, Li H, Chu J, Tarn T (2014) Fidelity-based probabilistic Q-learning for control of quantum systems. IEEE Trans Neur Netw Learn Syst 25(5):920\u2013933. https:\/\/doi.org\/10.1109\/TNNLS.2013.2283574","journal-title":"IEEE Trans Neur Netw Learn Syst"},{"issue":"1","key":"16_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2013.02.001","volume":"528","author":"MW Doherty","year":"2013","unstructured":"Doherty M W, Manson N B, Delaney P, Jelezko F, Wrachtrup J, Hollenberg L C L (2013) The nitrogen-vacancy colour centre in diamond. Phys Report 528(1):1\u201345. https:\/\/doi.org\/10.1016\/j.physrep.2013.02.001. arXiv:1302.3288","journal-title":"Phys Report"},{"key":"16_CR8","doi-asserted-by":"publisher","first-page":"031,084","DOI":"10.1103\/PhysRevX.8.031084","volume":"8","author":"T F\u00f6sel","year":"2018","unstructured":"F\u00f6sel T, Tighineanu P, Weiss T, Marquardt F (2018) Reinforcement learning with neural networks for quantum feedback. Phys Rev X 8:031,084. https:\/\/doi.org\/10.1103\/PhysRevX.8.031084","journal-title":"Phys Rev X"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Greiner JN, Dasari DBR, Wrachtrup J (2017) Purification of an unpolarized spin ensemble into entangled singlet pairs. Scientific Reports 7. https:\/\/doi.org\/10.1038\/s41598-017-00603-z. https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5428879\/","DOI":"10.1038\/s41598-017-00603-z"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Hasselt HV, Guez A, Silver D (2016) Deep reinforcement learning with double Q-learning. In: Proceedings of the 13th AAAI conference on artificial intelligence, AAAI Press, Phoenix, Arizona, AAAI\u201916, pp 2094\u20132100. http:\/\/dl.acm.org\/citation.cfm?id=3016100.3016191","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"16_CR11","unstructured":"Hausknecht M, Stone P (2015) Deep recurrent Q-learning, for partially observable MDPs. arXiv:1507.06527 [cs]"},{"key":"16_CR12","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. International Conference on Learning Representations"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Kriv\u00e1chy T, Cai Y, Cavalcanti D, Tavakoli A, Gisin N, Brunner N (2019) A neural network oracle for quantum nonlocality problems in networks. 1907.10552","DOI":"10.1038\/s41534-020-00305-x"},{"key":"16_CR14","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton EG (2012) ImageNet classification with deep convolutional neural networks. Neur Inf Process Syst 60:25. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Neur Inf Process Syst"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Lample G, Ott M, Conneau A, Denoyer L, Ranzato M (2018) Phrase-based, & neural unsupervised machine translation. arXiv:1804.07755 [cs]","DOI":"10.18653\/v1\/D18-1549"},{"key":"16_CR16","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. 1509.02971"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Mehta P, Bukov M, Wang C H, Day A G R, Richardson C, Fisher C K, Schwab D J (2018) A high-bias, low-variance introduction to machine learning for physicists. arXiv:1803.08823 [cond-mat, physics:physics, stat]","DOI":"10.1016\/j.physrep.2019.03.001"},{"issue":"6","key":"16_CR18","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1073\/pnas.1714936115","volume":"115","author":"AA Melnikov","year":"2018","unstructured":"Melnikov AA, Nautrup HP, Krenn M, Dunjko V, Tiersch M, Zeilinger A, Briegel HJ (2018) Active learning machine learns to create new quantum experiments. Proc Nat Acad Sci 115(6):1221\u20131226 . https:\/\/doi.org\/10.1073\/pnas.1714936115. https:\/\/www.pnas.org\/content\/115\/6\/1221","journal-title":"Proc Nat Acad Sci"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Melnikov AA, Fedichkin LE, Alodjants A (2019) Detecting quantum speedup by quantum walk with convolutional neural networks. 1901.10632","DOI":"10.1088\/1367-2630\/ab5c5e"},{"issue":"7540","key":"16_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/www.nature.com\/articles\/nature14236","journal-title":"Nature"},{"key":"16_CR21","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on international conference on machine learning, Omnipress, USA, ICML\u201910, pp 807\u2013814. http:\/\/dl.acm.org\/citation.cfm?id=3104322.3104425"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Nautrup HP, Delfosse N, Dunjko V, Briegel HJ, Friis N (2018) Optimizing quantum error correction codes with reinforcement learning. 1812.08451","DOI":"10.22331\/q-2019-12-16-215"},{"issue":"33","key":"16_CR23","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1038\/s41534-019-0141-3","volume":"5","author":"M Niu","year":"2019","unstructured":"Niu M, Boixo S, Vea S (2019) Universal quantum control through deep reinforcement learning. npj Quantum Inf 5(33):447\u2013450. https:\/\/doi.org\/10.1038\/s41534-019-0141-3","journal-title":"npj Quantum Inf"},{"issue":"61","key":"16_CR24","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/s42005-019-0169-x","volume":"2","author":"R Porotti","year":"2019","unstructured":"Porotti R, Tamascelli D, Mea Restelli (2019) Coherent transport of quantum states by deep reinforcement learning. Commun Phys 2(61):61. https:\/\/doi.org\/10.1038\/s42005-019-0169-x","journal-title":"Commun Phys"},{"key":"16_CR25","unstructured":"Real E, Moore S, Selle A, Saxena S, Suematsu YL, Tan J, Le Q, Kurakin A (2017) Large-scale evolution of image classifiers. arXiv:1703.01041 [cs]"},{"key":"16_CR26","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1038\/nature10401","volume":"477","author":"L Robledo","year":"2011","unstructured":"Robledo L, Childress L, Bernien H (2011) High-fidelity projective read-out of a solid-state spin quantum register. Nature 477:574\u2013578. https:\/\/doi.org\/10.1038\/nature10401","journal-title":"Nature"},{"issue":"6419","key":"16_CR27","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver D, Hubert T, Schrittwieser J, Antonoglou I, Lai M, Guez A, Lanctot M, Sifre L, Kumaran D, Graepel T, Lillicrap T, Simonyan K, Hassabis D (2018) A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419):1140\u20131144. https:\/\/doi.org\/10.1126\/science.aar6404. https:\/\/science.sciencemag.org\/content\/362\/6419\/1140","journal-title":"Science"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction","DOI":"10.1016\/S1474-6670(17)38315-5"},{"key":"16_CR29","unstructured":"Sweke R, Kesselring MS, van Nieuwenburg EPL, Eisert J (2018) Reinforcement learning decoders for fault-tolerant quantum computation. 1810.07207"},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1038\/s41567-018-0048-5","volume":"14","author":"G Torlai","year":"2018","unstructured":"Torlai G, Mazzola G, Carrasquilla J (2018) Neural-network quantum state tomography. Nature Phys 14:447\u2013450. https:\/\/doi.org\/10.1038\/s41567-018-0048-5","journal-title":"Nature Phys"},{"issue":"3","key":"16_CR31","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8(3):279\u2013292 . https:\/\/doi.org\/10.1007\/BF00992698","journal-title":"Mach Learn"},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.jmr.2016.06.017","volume":"269","author":"J Wrachtrup","year":"2016","unstructured":"Wrachtrup J, Finkler A (2016) Single spin magnetic resonance. J Magn Reson 269:225\u2013236. https:\/\/doi.org\/10.1016\/j.jmr.2016.06.017","journal-title":"J Magn Reson"}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-020-00016-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-020-00016-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-020-00016-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T11:49:45Z","timestamp":1666525785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-020-00016-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,11]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["16"],"URL":"https:\/\/doi.org\/10.1007\/s42484-020-00016-8","relation":{},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,11]]},"assertion":[{"value":"17 August 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interest"}}],"article-number":"5"}}