{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:11:48Z","timestamp":1742987508033,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031199448"},{"type":"electronic","value":"9783031199455"}],"license":[{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-19945-5_27","type":"book-chapter","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T16:06:26Z","timestamp":1666022786000},"page":"268-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Autonomous Navigation Using Model-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Siemen","family":"Herremans","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jens","family":"de Hoog","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Vanneste","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Balemans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Anwar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siegfried","family":"Mercelis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Hellinckx","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,18]]},"reference":[{"key":"27_CR1","first-page":"13","volume":"57","author":"P Thomas","year":"2013","unstructured":"Thomas, P., Morris, A., Talbot, R., Fagerlind, H.: Identifying the causes of road crashes in Europe. Ann. Adv. Automot. Med. 57, 13 (2013)","journal-title":"Ann. Adv. Automot. Med."},{"key":"27_CR2","first-page":"11","volume":"37","author":"S Grigorescu","year":"2019","unstructured":"Grigorescu, S., Trasnea, B., Cocias, T., Macesanu, G.: A survey of deep learning techniques for autonomous driving. J. Field Robot. 37, 11 (2019)","journal-title":"J. Field Robot."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2022)","DOI":"10.1109\/TITS.2021.3054625"},{"key":"27_CR4","doi-asserted-by":"publisher","unstructured":"Wu, J., Huang, Z., Lv, C.: Uncertainty-aware model-based reinforcement learning: methodology and application in autonomous driving. IEEE Trans. Intell. Veh. 1\u201310 (2022). https:\/\/doi.org\/10.1109\/TIV.2022.3185159","DOI":"10.1109\/TIV.2022.3185159"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","DOI":"10.1038\/s41586-020-03051-4"},{"key":"27_CR6","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR, vol. abs\/1707.06347 (2017). arxiv:1707.06347"},{"key":"27_CR7","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (2018)"},{"key":"27_CR8","unstructured":"Altman, E.: Constrained Markov Decision Processes: Stochastic Modeling. Routledge, Milton Park (1999)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"key":"27_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-540-75538-8_7","volume-title":"Computers and Games","author":"R Coulom","year":"2007","unstructured":"Coulom, R.: Efficient selectivity and backup operators in Monte-Carlo tree search. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M.J. (eds.) CG 2006. LNCS, vol. 4630, pp. 72\u201383. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75538-8_7"},{"key":"27_CR11","unstructured":"Silver, D., et al.: Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815 (2017)"},{"key":"27_CR12","doi-asserted-by":"publisher","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2), 235\u2013256 (2002). https:\/\/doi.org\/10.1023\/A:1013689704352","DOI":"10.1023\/A:1013689704352"},{"issue":"2","key":"27_CR13","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1109\/TIV.2019.2955905","volume":"5","author":"C Hoel","year":"2020","unstructured":"Hoel, C., Driggs-Campbell, K., Wolff, K., Laine, L., Kochenderfer, M.J.: Combining planning and deep reinforcement learning in tactical decision making for autonomous driving. IEEE Trans. Intell. Veh. 5(2), 294\u2013305 (2020)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"27_CR14","unstructured":"Yang, X., Duvaud, W., Wei, P.: Continuous control for searching and planning with a learned model. arXiv preprint arXiv:2006.07430 (2020)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Cou\u00ebtoux, A., Hoock, J.-B., Sokolovska, N., Teytaud, O., Bonnard, N.: Continuous upper confidence trees. In: LION 2011: Proceedings of the 5th International Conference on Learning and Intelligent OptimizatioN, Italy, 2011, p. TBA. https:\/\/hal.archives-ouvertes.fr\/hal-00542673","DOI":"10.1007\/978-3-642-25566-3_32"},{"key":"27_CR16","unstructured":"Moerland, T.M., Broekens, J., Plaat, A., Jonker, C.M.: A0C: alpha zero in continuous action space. arXiv preprint arXiv:1805.09613 (2018)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Chaslot, G., Winands, M., Herik, H., Uiterwijk, J., Bouzy, B.: Progressive strategies for Monte-Carlo tree search. New Math. Nat. Comput. 4, 343\u2013357 (2008)","DOI":"10.1142\/S1793005708001094"},{"key":"27_CR18","unstructured":"Henderson, T.: Mit racecar simulator. https:\/\/github.com\/mit-racecar\/racecar_simulator (2017)"},{"key":"27_CR19","unstructured":"Behrens, F.: Procedural race track generation for domain randomization (2020)"},{"key":"27_CR20","unstructured":"Liang, E., et al.: RLlib: abstractions for distributed reinforcement learning. In: International Conference on Machine Learning. PMLR 2018, pp. 3053\u20133062 (2018)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Tang, Y., Agrawal, S.: Discretizing continuous action space for on-policy optimization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, no.\u00a004, pp. 5981\u20135988 (2020). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6059","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"27_CR22","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-030-89899-1_24","volume-title":"Advances on P2P, Parallel, Grid, Cloud and Internet Computing","author":"A Troch","year":"2022","unstructured":"Troch, A., Hoog, J., Vanneste, S., Balemans, D., Latr\u00e9, S., Hellinckx, P.: Transfer learning in autonomous driving using real-world samples. In: Barolli, L. (ed.) 3PGCIC 2021. LNNS, vol. 343, pp. 237\u2013245. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-89899-1_24"}],"container-title":["Lecture Notes in Networks and Systems","Advances on P2P, Parallel, Grid, Cloud and Internet Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19945-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T16:07:37Z","timestamp":1666022857000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19945-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,18]]},"ISBN":["9783031199448","9783031199455"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19945-5_27","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022,10,18]]},"assertion":[{"value":"18 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"3PGCIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on P2P, Parallel, Grid, Cloud and Internet Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tirana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Albania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pgcic2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/3pgcic\/2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}