{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T21:06:46Z","timestamp":1778274406242,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"7896","license":[{"start":{"date-parts":[[2022,2,9]],"date-time":"2022-02-09T00:00:00Z","timestamp":1644364800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,9]],"date-time":"2022-02-09T00:00:00Z","timestamp":1644364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2022,2,10]]},"DOI":"10.1038\/s41586-021-04357-7","type":"journal-article","created":{"date-parts":[[2022,2,9]],"date-time":"2022-02-09T12:03:02Z","timestamp":1644408182000},"page":"223-228","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":310,"title":["Outracing champion Gran Turismo drivers with deep reinforcement learning"],"prefix":"10.1038","volume":"602","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9349-0624","authenticated-orcid":false,"given":"Peter R.","family":"Wurman","sequence":"first","affiliation":[]},{"given":"Samuel","family":"Barrett","sequence":"additional","affiliation":[]},{"given":"Kenta","family":"Kawamoto","sequence":"additional","affiliation":[]},{"given":"James","family":"MacGlashan","sequence":"additional","affiliation":[]},{"given":"Kaushik","family":"Subramanian","sequence":"additional","affiliation":[]},{"given":"Thomas J.","family":"Walsh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2219-215X","authenticated-orcid":false,"given":"Roberto","family":"Capobianco","sequence":"additional","affiliation":[]},{"given":"Alisa","family":"Devlic","sequence":"additional","affiliation":[]},{"given":"Franziska","family":"Eckert","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1072-3718","authenticated-orcid":false,"given":"Florian","family":"Fuchs","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9741-2014","authenticated-orcid":false,"given":"Leilani","family":"Gilpin","sequence":"additional","affiliation":[]},{"given":"Piyush","family":"Khandelwal","sequence":"additional","affiliation":[]},{"given":"Varun","family":"Kompella","sequence":"additional","affiliation":[]},{"given":"HaoChih","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"MacAlpine","sequence":"additional","affiliation":[]},{"given":"Declan","family":"Oller","sequence":"additional","affiliation":[]},{"given":"Takuma","family":"Seno","sequence":"additional","affiliation":[]},{"given":"Craig","family":"Sherstan","sequence":"additional","affiliation":[]},{"given":"Michael D.","family":"Thomure","sequence":"additional","affiliation":[]},{"given":"Houmehr","family":"Aghabozorgi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9896-3259","authenticated-orcid":false,"given":"Leon","family":"Barrett","sequence":"additional","affiliation":[]},{"given":"Rory","family":"Douglas","sequence":"additional","affiliation":[]},{"given":"Dion","family":"Whitehead","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3840-5009","authenticated-orcid":false,"given":"Peter","family":"D\u00fcrr","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9443-7008","authenticated-orcid":false,"given":"Michael","family":"Spranger","sequence":"additional","affiliation":[]},{"given":"Hiroaki","family":"Kitano","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,9]]},"reference":[{"key":"4357_CR1","unstructured":"Milliken, W. F. et al. Race Car Vehicle Dynamics Vol. 400 (Society of Automotive Engineers, 1995)."},{"key":"4357_CR2","unstructured":"Mnih, V. et al. Playing Atari with deep reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/1312.5602 (2013)."},{"key":"4357_CR3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016).","journal-title":"Nature"},{"key":"4357_CR4","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D. et al. Mastering the game of Go without human knowledge. Nature 550, 354\u2013359 (2017).","journal-title":"Nature"},{"key":"4357_CR5","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O. et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019).","journal-title":"Nature"},{"key":"4357_CR6","unstructured":"Berner, C. et al. Dota 2 with large scale deep reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/1912.06680 (2019)."},{"key":"4357_CR7","doi-asserted-by":"crossref","unstructured":"Laurense, V. A., Goh, J. Y. & Gerdes, J. C. In 2017 American Control Conference (ACC) 5586\u20135591 (IEEE, 2017).","DOI":"10.23919\/ACC.2017.7963824"},{"key":"4357_CR8","doi-asserted-by":"publisher","first-page":"eaaw1975","DOI":"10.1126\/scirobotics.aaw1975","volume":"4","author":"NA Spielberg","year":"2019","unstructured":"Spielberg, N. A., Brown, M., Kapania, N. R., Kegelman, J. C. & Gerdes, J. C. Neural network vehicle models for high-performance automated driving. Sci. Robot. 4, eaaw1975 (2019).","journal-title":"Sci. Robot."},{"key":"4357_CR9","unstructured":"Burke, K. Data makes it beta: Roborace returns for second season with updateable self-driving vehicles powered by NVIDIA DRIVE. The Official NVIDIA Blog https:\/\/blogs.nvidia.com\/blog\/2020\/10\/29\/roborace-second-season-nvidia-drive\/ (2020)."},{"key":"4357_CR10","unstructured":"Leporati, G. No driver? no problem\u2014this is the Indy Autonomous Challenge. Ars Technica https:\/\/arstechnica.com\/cars\/2021\/07\/a-science-fair-or-the-future-of-racing-the-indy-autonomous-challenge\/ (2021)."},{"key":"4357_CR11","unstructured":"Williams, G., Drews, P., Goldfain, B., Rehg, J. M. & Theodorou, E. A. In 2016 IEEE International Conference on Robotics and Automation (ICRA) 1433\u20131440 (IEEE, 2016)."},{"key":"4357_CR12","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1109\/TRO.2018.2865891","volume":"34","author":"G Williams","year":"2018","unstructured":"Williams, G., Drews, P., Goldfain, B., Rehg, J. M. & Theodorou, E. A. Information-theoretic model predictive control: theory and applications to autonomous driving. IEEE Trans. Robot. 34, 1603\u20131622 (2018).","journal-title":"IEEE Trans. Robot."},{"key":"4357_CR13","doi-asserted-by":"publisher","unstructured":"Pan, Y. et al. In Proc. Robotics: Science and Systems XIV (eds Kress-Gazit, H., Srinivasa, S., Howard, T. & Atanasov, N.) https:\/\/doi.org\/10.15607\/RSS.2018.XIV.056 (Carnegie Mellon Univ., 2018).","DOI":"10.15607\/RSS.2018.XIV.056"},{"key":"4357_CR14","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1177\/0278364919880273","volume":"39","author":"Y Pan","year":"2020","unstructured":"Pan, Y. et al. Imitation learning for agile autonomous driving. Int. J. Robot. Res. 39, 286\u2013302 (2020).","journal-title":"Int. J. Robot. Res."},{"key":"4357_CR15","unstructured":"Amazon Web Services. AWS DeepRacer League. https:\/\/aws.amazon.com\/deepracer\/league\/ (2019)."},{"key":"4357_CR16","unstructured":"Pyeatt, L. D. & Howe, A. E. Learning to race: experiments with a simulated race car. In Proc. Eleventh International FLAIRS Conference 357\u2013361 (AAAI, 1998)."},{"key":"4357_CR17","doi-asserted-by":"crossref","unstructured":"Chaperot, B. & Fyfe, C. In 2006 IEEE Symposium on Computational Intelligence and Games 181\u2013186 (IEEE, 2006).","DOI":"10.1109\/CIG.2006.311698"},{"key":"4357_CR18","doi-asserted-by":"crossref","unstructured":"Cardamone, L., Loiacono, D. & Lanzi, P. L. In Proc. 11th Annual Conference on Genetic and Evolutionary Computation 1179\u20131186 (ACM, 2009).","DOI":"10.1145\/1569901.1570060"},{"key":"4357_CR19","doi-asserted-by":"crossref","unstructured":"Cardamone, L., Loiacono, D. & Lanzi, P. L. In 2009 IEEE Congress on Evolutionary Computation 2622\u20132629 (IEEE, 2009).","DOI":"10.1109\/CEC.2009.4983271"},{"key":"4357_CR20","doi-asserted-by":"crossref","unstructured":"Loiacono, D., Prete, A., Lanzi, L. & Cardamone, L. In IEEE Congress on Evolutionary Computation 1\u20138 (IEEE, 2010).","DOI":"10.1109\/CEC.2010.5586191"},{"key":"4357_CR21","unstructured":"Jaritz, M., de Charette, R., Toromanoff, M., Perot, E. & Nashashibi, F. In 2018 IEEE International Conference on Robotics and Automation (ICRA) 2070\u20132075 (IEEE, 2018)."},{"key":"4357_CR22","unstructured":"Weiss, T. & Behl, M. In 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) 1163\u20131168 (IEEE, 2020)."},{"key":"4357_CR23","unstructured":"Weiss, T., Babu, V. S. & Behl, M. In NeurIPS 2020 Workshop on Machine Learning for Autonomous Driving (NeurIPS, 2020)."},{"key":"4357_CR24","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.1109\/LRA.2021.3064284","volume":"6","author":"F Fuchs","year":"2021","unstructured":"Fuchs, F., Song, Y., Kaufmann, E., Scaramuzza, D. & D\u00fcrr, P. Super-human performance in Gran Turismo Sport using deep reinforcement learning. IEEE Robot. Autom. Lett. 6, 4257\u20134264 (2021).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"4357_CR25","unstructured":"Song, Y., Lin, H., Kaufmann, E., D\u00fcrr, P. & Scaramuzza, D. In Proc. IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2021)."},{"key":"4357_CR26","unstructured":"Theodosis, P. A. & Gerdes, J. C. In Dynamic Systems and Control Conference Vol. 45295, 235\u2013241 (American Society of Mechanical Engineers, 2012)."},{"key":"4357_CR27","unstructured":"Funke, J. et al. In 2012 IEEE Intelligent Vehicles Symposium 541\u2013547 (IEEE, 2012)."},{"key":"4357_CR28","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1504\/IJVAS.2012.051270","volume":"10","author":"K Kritayakirana","year":"2012","unstructured":"Kritayakirana, K. & Gerdes, J. C. Autonomous vehicle control at the limits of handling. Int. J. Veh. Auton. Syst. 10, 271\u2013296 (2012).","journal-title":"Int. J. Veh. Auton. Syst."},{"key":"4357_CR29","unstructured":"Bonkowski, J. Here\u2019s what you missed from the Indy Autonomous Challenge main event. Autoweek https:\/\/www.autoweek.com\/racing\/more-racing\/a38069263\/what-missed-indy-autonomous-challenge-main-event\/ (2021)."},{"key":"4357_CR30","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1504\/IJVD.2010.034101","volume":"53","author":"SJ Rutherford","year":"2010","unstructured":"Rutherford, S. J. & Cole, D. J. Modelling nonlinear vehicle dynamics with neural networks. Int. J. Veh. Des. 53, 260\u2013287 (2010).","journal-title":"Int. J. Veh. Des."},{"key":"4357_CR31","doi-asserted-by":"crossref","unstructured":"Pomerleau, D. A. In Robot Learning (eds Connell, J. H. & Mahadevan, S.) 19\u201343 (Springer, 1993).","DOI":"10.1007\/978-1-4615-3184-5_2"},{"key":"4357_CR32","unstructured":"Togelius, J. & Lucas, S. M. In 2006 IEEE International Conference on Evolutionary Computation 1187\u20131194 (IEEE, 2006)."},{"key":"4357_CR33","unstructured":"Schwarting, W. et al. Deep latent competition: learning to race using visual control policies in latent space. Preprint at https:\/\/arxiv.org\/abs\/2102.09812 (2021)."},{"key":"4357_CR34","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.humov.2014.09.004","volume":"38","author":"DG Gozli","year":"2014","unstructured":"Gozli, D. G., Bavelier, D. & Pratt, J. The effect of action video game playing on sensorimotor learning: evidence from a movement tracking task. Hum. Mov. Sci. 38, 152\u2013162 (2014).","journal-title":"Hum. Mov. Sci."},{"key":"4357_CR35","doi-asserted-by":"crossref","unstructured":"Davids, K., Williams, A. M. & Williams, J. G. Visual Perception and Action in Sport (Routledge, 2005).","DOI":"10.4324\/9780203979952"},{"key":"4357_CR36","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P. & Levine, S. In Proc. 35th International Conference on Machine Learning 1856\u20131865 (PMLR, 2018)."},{"key":"4357_CR37","unstructured":"Haarnoja, T. et al. Soft actor-critic algorithms and applications. Preprint at https:\/\/arxiv.org\/abs\/1812.05905 (2018)."},{"key":"4357_CR38","unstructured":"Mnih, V. et al. In Proc. 33rd International Conference on Machine Learning 1928\u20131937 (PMLR, 2016)."},{"key":"4357_CR39","doi-asserted-by":"crossref","unstructured":"Dabney, W., Rowland, M., Bellemare, M. G. & Munos, R. In 32nd AAAI Conference on Artificial Intelligence (AAAI, 2018).","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"4357_CR40","unstructured":"Lin, L.-J. Reinforcement Learning for Robots Using Neural Networks. Dissertation, Carnegie Mellon Univ. (1993)."},{"key":"4357_CR41","unstructured":"Siu, H. C. et al. Evaluation of human-AI teams for learned and rule-based agents in Hanabi. Preprint at https:\/\/arxiv.org\/abs\/2107.07630 (2021)."},{"key":"4357_CR42","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G Tesauro","year":"1994","unstructured":"Tesauro, G. TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6, 215\u2013219 (1994).","journal-title":"Neural Comput."},{"key":"4357_CR43","unstructured":"Devore, J. L. Probability and Statistics for Engineering and the Sciences 6th edn (Brooks\/Cole, 2004)."},{"key":"4357_CR44","unstructured":"Xia, L., Zhou, Z., Yang, J. & Zhao, Q. DSAC: distributional soft actor critic for risk-sensitive reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/2004.14547 (2020)."},{"key":"4357_CR45","unstructured":"Fujimoto, S., van Hoof, H. & Meger, D. In Proc. 35th International Conference on Machine Learning 1587\u20131596 (PMLR, 2018)."},{"key":"4357_CR46","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014).","journal-title":"J. Mach. Learn. Res."},{"key":"4357_CR47","unstructured":"Liu, Z., Li, X., Kang, B. & Darrell, T. In International Conference on Learning Representations (ICLR, 2021)."},{"key":"4357_CR48","unstructured":"Kingma, D. P. & Ba, J. In International Conference on Learning Representations (ICLR, 2015)."},{"key":"4357_CR49","unstructured":"Cassirer, A. et al. Reverb: a framework for experience replay. Preprint at https:\/\/arxiv.org\/abs\/2102.04736 (2021)."},{"key":"4357_CR50","unstructured":"Narvekar, S., Sinapov, J., Leonetti, M. & Stone, P. In Proc. 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016) (2016)."}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-021-04357-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-021-04357-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-021-04357-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T01:42:42Z","timestamp":1726623762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-021-04357-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,9]]},"references-count":50,"journal-issue":{"issue":"7896","published-print":{"date-parts":[[2022,2,10]]}},"alternative-id":["4357"],"URL":"https:\/\/doi.org\/10.1038\/s41586-021-04357-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-795954\/v1","asserted-by":"object"}]},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,9]]},"assertion":[{"value":"9 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"\u00a0P.R.W. and other team members have submitted US provisional patent application\u00a063\/267,136\u00a0covering aspects of the scenario training techniques described in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}