{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:01:01Z","timestamp":1790697661417,"version":"4.1.0"},"reference-count":40,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"36","license":[{"start":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T00:00:00Z","timestamp":1599004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-StG 757634"],"award-info":[{"award-number":["ERC-StG 757634"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["SFB 1083"],"award-info":[{"award-number":["SFB 1083"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["Math+"],"award-info":[{"award-number":["Math+"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["EXC 2046\/1"],"award-info":[{"award-number":["EXC 2046\/1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS14013A-E"],"award-info":[{"award-number":["01IS14013A-E"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01GQ1115"],"award-info":[{"award-number":["01GQ1115"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01GQ0850"],"award-info":[{"award-number":["01GQ0850"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","award":["2017-0-01779"],"award-info":[{"award-number":["2017-0-01779"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sci. Adv."],"published-print":{"date-parts":[[2020,9,4]]},"abstract":"<jats:p>Intelligent learning agent controls a scanning probe microscope and masters a nanoscale robotic task of molecule manipulation.<\/jats:p>","DOI":"10.1126\/sciadv.abb6987","type":"journal-article","created":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T19:15:51Z","timestamp":1599074151000},"source":"Crossref","is-referenced-by-count":79,"title":["Autonomous robotic nanofabrication with reinforcement learning"],"prefix":"10.1126","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9900-2107","authenticated-orcid":true,"given":"Philipp","family":"Leinen","sequence":"first","affiliation":[{"name":"Peter Gr\u00fcnberg Institut (PGI-3), Forschungszentrum J\u00fclich, 52425 J\u00fclich, Germany."},{"name":"J\u00fclich Aachen Research Alliance (JARA)\u2013Fundamentals of Future Information Technology, 52425 J\u00fclich, Germany."},{"name":"Experimentalphysik IV A, RWTH Aachen University, Otto-Blumenthal-Stra\u00dfe, 52074 Aachen, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9136-914X","authenticated-orcid":true,"given":"Malte","family":"Esders","sequence":"additional","affiliation":[{"name":"Machine Learning Group, Technische Universit\u00e4t Berlin, 10587 Berlin, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8342-0964","authenticated-orcid":true,"given":"Kristof T.","family":"Sch\u00fctt","sequence":"additional","affiliation":[{"name":"Machine Learning Group, Technische Universit\u00e4t Berlin, 10587 Berlin, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2117-6289","authenticated-orcid":true,"given":"Christian","family":"Wagner","sequence":"additional","affiliation":[{"name":"Peter Gr\u00fcnberg Institut (PGI-3), Forschungszentrum J\u00fclich, 52425 J\u00fclich, Germany."},{"name":"J\u00fclich Aachen Research Alliance (JARA)\u2013Fundamentals of Future Information Technology, 52425 J\u00fclich, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3861-7685","authenticated-orcid":true,"given":"Klaus-Robert","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Machine Learning Group, Technische Universit\u00e4t Berlin, 10587 Berlin, Germany."},{"name":"Max Planck Institute for Informatics, 66123 Saarbr\u00fccken, Germany."},{"name":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3583-2379","authenticated-orcid":true,"given":"F. Stefan","family":"Tautz","sequence":"additional","affiliation":[{"name":"Peter Gr\u00fcnberg Institut (PGI-3), Forschungszentrum J\u00fclich, 52425 J\u00fclich, Germany."},{"name":"J\u00fclich Aachen Research Alliance (JARA)\u2013Fundamentals of Future Information Technology, 52425 J\u00fclich, Germany."},{"name":"Experimentalphysik IV A, RWTH Aachen University, Otto-Blumenthal-Stra\u00dfe, 52074 Aachen, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/10\/5\/053012"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1168255"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/nnano.2012.169"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms6568"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201502868"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad3569"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0223-y"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.1218"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.275.5304.1295"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.283.5408.1683"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/479187a"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-016-0005"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1207598"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"J. Gl\u00fcckstad D. Palima A. Ba\u00f1as Light robotics: Aiming towards all-optical nano-robotics in The Proceedings of the Optical Manipulation Conference (2017) p. 102520C.","DOI":"10.1117\/12.2270422"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"e_1_3_2_18_2","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine S.","year":"2016","unstructured":"S. Levine, C. Finn, T. Darrell, P. Abbeel, End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17, 1\u201340 (2016).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_19_2","unstructured":"M. Andrychowicz F. Wolski A. Ray J. Schneider R. Fong P. Welinder B. McGrew J. Tobin P. Abbeel W. Zaremba Hindsight experience replay in 31st Conference on Neural Information Processing Systems (NIPS 2017) Long Beach CA USA (2017)."},{"key":"e_1_3_2_20_2","unstructured":"R. S. Sutton A. G. Barto Reinforcement Learning: An Introduction (MIT Press ed. 2 2018)."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aag2302"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.3762\/bjnano.5.203"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.8b03960"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3762\/bjnano.6.220"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.115.026101"},{"key":"e_1_3_2_26_2","first-page":"54506","article-title":"Hand controlled manipulation of single molecules via a scanning probe microscope with a 3D virtual reality interface","author":"Leinen P.","year":"2016","unstructured":"P. Leinen, M. F. B. Green, T. Esat, C. Wagner, F. S. Tautz, R. Temirov, Hand controlled manipulation of single molecules via a scanning probe microscope with a 3D virtual reality interface. J. Vis. Exp., 54506 (2016).","journal-title":"J. Vis. Exp."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.206801"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41563-019-0382-8"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.84.035435"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"H. van Seijen H. van Hasselt S. Whiteson M. Wiering A theoretical and empirical analysis of Expected Sarsa in Proceedings of the 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2009) (2009) pp. 177\u2013184.","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"e_1_3_2_31_2","unstructured":"T. Schaul J. Quan I. Antonoglou D. Silver Prioritized experience replay in 4th International Conference on Learning Representations (ICLR 2016) San Juan Puerto Rico (2016)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.5052264"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1021\/acsnano.8b02208"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.5099590"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42005-020-0317-3"},{"key":"e_1_3_2_37_2","unstructured":"S. Thrun A. Schwartz Issues in using function approximation for reinforcement learning in Proceedings of the 4th Connectionist Models Summer School (Lawrence Erlbaum Publisher 1993)."},{"key":"e_1_3_2_38_2","unstructured":"H. van Hasselt Double Q-learning in Annual Conference on Advances in Neural Information Processing Systems (2010) pp. 2613\u20132621."},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"H. van Hasselt A. Guez D. Silver Deep reinforcement learning with double Q-learning in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (2016) pp. 2094\u20132100.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_40_2","unstructured":"Z. Wang T. Schaul M. Hessel H. van Hasselt M. Lanctot N. de Freitas Dueling network architectures for deep reinforcement learning in Proceedings of the 33rd International Conference on Machine Learning (ICML) (2016) pp. 1995\u20132003."},{"key":"e_1_3_2_41_2","unstructured":"D. P. Kingma J. Ba Adam: A method for stochastic optimization in 3rd International Conference on Learning Representations (ICLR 2015) San Diego (2015)."}],"container-title":["Science Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1126\/sciadv.abb6987","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/sciadv.abb6987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T14:23:04Z","timestamp":1704810184000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/sciadv.abb6987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,4]]},"references-count":40,"journal-issue":{"issue":"36","published-print":{"date-parts":[[2020,9,4]]}},"alternative-id":["10.1126\/sciadv.abb6987"],"URL":"https:\/\/doi.org\/10.1126\/sciadv.abb6987","relation":{},"ISSN":["2375-2548"],"issn-type":[{"value":"2375-2548","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,4]]},"article-number":"eabb6987"}}