{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T14:22:07Z","timestamp":1761920527511,"version":"3.41.2"},"reference-count":15,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"26","license":[{"start":{"date-parts":[[2019,1,16]],"date-time":"2019-01-16T00:00:00Z","timestamp":1547596800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.sciencemag.org\/about\/science-licenses-journal-article-reuse"}],"funder":[{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["097490"],"award-info":[{"award-number":["097490"]}],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000341","name":"Arthritis Research UK","doi-asserted-by":"publisher","award":["21357"],"award-info":[{"award-number":["21357"]}],"id":[{"id":"10.13039\/501100000341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","award":["2017-0-00451"],"award-info":[{"award-number":["2017-0-00451"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","award":["2018-0-00677"],"award-info":[{"award-number":["2018-0-00677"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Samsung Research Funding Center of Samsung Electronics","award":["SRFC-TC1603-06"],"award-info":[{"award-number":["SRFC-TC1603-06"]}]},{"name":"ICT R&D program of Ministry of Science, ICT and Future Planning and Institute for Information and Communications Technology Promotion","award":["2016-0-00563"],"award-info":[{"award-number":["2016-0-00563"]}]},{"name":"The research fund of the KAIST","award":["G04150045"],"award-info":[{"award-number":["G04150045"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2019,1,30]]},"abstract":"<jats:p>Insights from decision neuroscience raise hope for intelligent brain-inspired solutions to robot learning in real dynamic environments.<\/jats:p>","DOI":"10.1126\/scirobotics.aav2975","type":"journal-article","created":{"date-parts":[[2019,1,17]],"date-time":"2019-01-17T00:15:11Z","timestamp":1547684111000},"source":"Crossref","is-referenced-by-count":9,"title":["Toward high-performance, memory-efficient, and fast reinforcement learning\u2014Lessons from decision neuroscience"],"prefix":"10.1126","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4337-2774","authenticated-orcid":true,"given":"Jee Hang","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Bio and Brain Engineering, KAIST, Daejeon, Republic of Korea."},{"name":"KAIST Institute for Health Science and Technology, Daejeon, Republic of Korea."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1724-5832","authenticated-orcid":true,"given":"Ben","family":"Seymour","sequence":"additional","affiliation":[{"name":"Computational and Biological Learning Laboratory, Department of Engineering, University of Cambridge, Trumpington Street, Cambridge CB2 1PZ, UK."},{"name":"Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institute International, Kyoto, Japan."},{"name":"Center for Information and Neural Networks, National Institute of Information and Communications Technology, 1-4 Yamadaoka, Suita, Osaka 565-0871, Japan."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3153-916X","authenticated-orcid":true,"given":"Joel Z.","family":"Leibo","sequence":"additional","affiliation":[{"name":"DeepMind, London, UK."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4232-2799","authenticated-orcid":true,"given":"Su Jin","family":"An","sequence":"additional","affiliation":[{"name":"Department of Bio and Brain Engineering, KAIST, Daejeon, Republic of Korea."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-9613","authenticated-orcid":true,"given":"Sang Wan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Bio and Brain Engineering, KAIST, Daejeon, Republic of Korea."},{"name":"KAIST Institute for Health Science and Technology, Daejeon, Republic of Korea."},{"name":"KAIST Institute for Artificial Intelligence, Daejeon, Republic of Korea."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/nn1560"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","unstructured":"S. Elfwing B. J. Seymour Parallel reward and punishment control in humans and robots: Safe reinforcement learning using the MaxPain algorithm in 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2017) (2018) vol. 2018 pp. 140\u2013147.","DOI":"10.1109\/DEVLRN.2017.8329799"},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","first-page":"e1002137","DOI":"10.1371\/journal.pbio.1002137","article-title":"Neural computations mediating one-shot learning in the human brain","volume":"13","author":"Lee S. W.","year":"2015","unstructured":"S. W. Lee, J. P. O\u2019Doherty, S. Shimojo, Neural computations mediating one-shot learning in the human brain. PLOS Biol. 13, e1002137 (2015).","journal-title":"PLOS Biol."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/nn1954"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1016\/j.neuron.2013.11.028","article-title":"Neural computations underlying arbitration between model-based and model-free learning","volume":"81","author":"Lee S. W.","year":"2014","unstructured":"S. W. Lee, S. Shimojo, J. P. O\u2019Doherty, Neural computations underlying arbitration between model-based and model-free learning. Neuron 81, 687\u2013699 (2014).","journal-title":"Neuron"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0147-8"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1146\/annurev.soc.24.1.183","article-title":"Social dilemmas: The anatomy of cooperation","volume":"24","author":"Kollock P.","year":"1998","unstructured":"P. Kollock, Social dilemmas: The anatomy of cooperation. Annu. Rev. Soc. 24, 183\u2013214 (1998).","journal-title":"Annu. Rev. Soc."},{"key":"e_1_3_1_11_2","unstructured":"M. Kleiman-Weiner M. K. Ho J. L. Austerweil M. L. Littman J. B. Tenenbaum Coordinate to cooperate or compete: Abstract goals and joint intentions in social interaction in Proceedings of the 38th Annual Meeting of the Cognitive Science Society (2016) pp. 1679\u20131684."},{"key":"e_1_3_1_12_2","unstructured":"A. Lerer A. Peysakhovich Maintaining cooperation in complex social dilemmas using deep reinforcement learning https:\/\/arxiv.org\/abs\/1707.01068 (2017)."},{"key":"e_1_3_1_13_2","unstructured":"J. Foerster R. Y. Chen M. Al-Shedivat S. Whiteson P. Abbeel I. Mordatch Learning with opponent-learning awareness in Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (International Foundation for Autonomous Agents and Multiagent Systems 2018) pp. 122\u2013130."},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","first-page":"443","DOI":"10.3389\/fnhum.2014.00443","article-title":"How to measure metacognition","volume":"8","author":"Fleming S. M.","year":"2014","unstructured":"S. M. Fleming, H. C. Lau, How to measure metacognition. Front. Hum. Neurosci. 8, 443 (2014).","journal-title":"Front. Hum. Neurosci."},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1016\/j.tics.2015.08.013","article-title":"Deciding how to decide: Self-control and meta-decision making","volume":"19","author":"Boureau Y.-L.","year":"2015","unstructured":"Y.-L. Boureau, P. Sokol-Hessner, N. D. Daw, Deciding how to decide: Self-control and meta-decision making. Trends Cogn. Sci. 19, 700\u2013710 (2015).","journal-title":"Trends Cogn. Sci."},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.cobeha.2014.10.007","article-title":"Executive control and decision-making in the prefrontal cortex","volume":"1","author":"Domenech P.","year":"2015","unstructured":"P. Domenech, E. Koechlin, Executive control and decision-making in the prefrontal cortex. Curr. Opin. Behav. Sci. 1, 101\u2013106 (2015).","journal-title":"Curr. Opin. Behav. Sci."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1126\/scirobotics.aav2975","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.aav2975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T12:23:27Z","timestamp":1705407807000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.aav2975"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,30]]},"references-count":15,"journal-issue":{"issue":"26","published-print":{"date-parts":[[2019,1,30]]}},"alternative-id":["10.1126\/scirobotics.aav2975"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.aav2975","relation":{},"ISSN":["2470-9476"],"issn-type":[{"type":"electronic","value":"2470-9476"}],"subject":[],"published":{"date-parts":[[2019,1,30]]},"article-number":"eaav2975"}}