{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:04:20Z","timestamp":1743127460268,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031831164"},{"type":"electronic","value":"9783031831171"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-83117-1_26","type":"book-chapter","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T19:17:56Z","timestamp":1740597476000},"page":"274-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quick Insights: Reinforcement Learning in\u00a0Autonomous Driving A Short Review"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0603-7686","authenticated-orcid":false,"given":"Samuel","family":"Adrados","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6279-1189","authenticated-orcid":false,"given":"Javier","family":"Curto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfonso","family":"Gonz\u00e1lez-Briones","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5109-3583","authenticated-orcid":false,"given":"Pablo","family":"Chamoso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Abdalameer, H., Al-Shammary, A.: Self- driving with deep reinforcement (survey). J. Al-Qadisiyah Comput. Sci. Math. 14 (2022). https:\/\/doi.org\/10.29304\/jqcm.2022.14.3.982","DOI":"10.29304\/jqcm.2022.14.3.982"},{"issue":"2","key":"26_CR2","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TITS.2020.3024655","volume":"23","author":"S Aradi","year":"2022","unstructured":"Aradi, S.: Survey of deep reinforcement learning for motion planning of autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23(2), 740\u2013759 (2022). https:\/\/doi.org\/10.1109\/TITS.2020.3024655","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"26_CR3","volume-title":"Dynamic Programming","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming, 1st edn. Princeton University Press, Princeton (1957)","edition":"1"},{"key":"26_CR4","unstructured":"Coggan, M.: Exploration and exploitation in reinforcement learning. Research supervised by Prof. Doina Precup, CRA-W DMP Project at McGill University (2004)"},{"key":"26_CR5","doi-asserted-by":"publisher","unstructured":"Deng, H., Zhao, Y., Wang, Q., Nguyen, A.T.: Deep reinforcement learning based decision-making strategy of autonomous vehicle in highway uncertain driving environments. Autom. Innov. 6 (2023). https:\/\/doi.org\/10.1007\/s42154-023-00231-6","DOI":"10.1007\/s42154-023-00231-6"},{"key":"26_CR6","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A.M., Koltun, V.: CARLA: an open urban driving simulator. CoRR abs\/1711.03938 (2017). http:\/\/arxiv.org\/abs\/1711.03938"},{"key":"26_CR7","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. CoRR abs\/1812.05905 (2018). http:\/\/arxiv.org\/abs\/1812.05905"},{"key":"26_CR8","unstructured":"Hasselt, H.V., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI 2016, pp. 2094\u20132100. AAAI Press (2016)"},{"key":"26_CR9","doi-asserted-by":"publisher","unstructured":"Kiangala, K.S., Wang, Z.: An experimental safety response mechanism for an autonomous moving robot in a smart manufacturing environment using Q-learning algorithm and speech recognition. Sensors 22(3) (2022). https:\/\/doi.org\/10.3390\/s22030941, https:\/\/www.mdpi.com\/1424-8220\/22\/3\/941","DOI":"10.3390\/s22030941"},{"key":"26_CR10","doi-asserted-by":"publisher","unstructured":"Kiran, B., Sobh, I., Talpaert, V., Mannion, P., Sallab, A., Yogamani, S., Perez, P.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. PP, 1\u201318 (2021). https:\/\/doi.org\/10.1109\/TITS.2021.3054625","DOI":"10.1109\/TITS.2021.3054625"},{"key":"26_CR11","doi-asserted-by":"publisher","unstructured":"Koenig, N., Howard, A.: Design and use paradigms for gazebo, an open-source multi-robot simulator. In: 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566), vol.\u00a03, pp. 2149\u20132154 (2004). https:\/\/doi.org\/10.1109\/IROS.2004.1389727","DOI":"10.1109\/IROS.2004.1389727"},{"key":"26_CR12","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. CoRR abs\/1509.02971 (2015). https:\/\/api.semanticscholar.org\/CorpusID:16326763"},{"key":"26_CR13","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. CoRR abs\/1602.01783 (2016). http:\/\/arxiv.org\/abs\/1602.01783"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015). https:\/\/api.semanticscholar.org\/CorpusID:205242740","DOI":"10.1038\/nature14236"},{"issue":"3","key":"26_CR15","doi-asserted-by":"publisher","first-page":"2967","DOI":"10.1007\/s10489-022-03550-z","volume":"53","author":"ND Nguyen","year":"2022","unstructured":"Nguyen, N.D., et al.: Towards designing a generic and comprehensive deep reinforcement learning framework. Appl. Intell. 53(3), 2967\u20132988 (2022). https:\/\/doi.org\/10.1007\/s10489-022-03550-z","journal-title":"Appl. Intell."},{"key":"26_CR16","unstructured":"Rummery, G., Niranjan, M.: On-line Q-learning using connectionist systems. Technical report CUED\/F-INFENG\/TR 166 (1994)"},{"key":"26_CR17","unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M.I., Abbeel, P.: Trust region policy optimization. CoRR abs\/1502.05477 (2015). http:\/\/arxiv.org\/abs\/1502.05477"},{"key":"26_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017). http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"26_CR19","unstructured":"Shah, S., Dey, D., Lovett, C., Kapoor, A.: Airsim: High-fidelity visual and physical simulation for autonomous vehicles. CoRR abs\/1705.05065 (2017). http:\/\/arxiv.org\/abs\/1705.05065"},{"key":"26_CR20","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Xing, E.P., Jebara, T. (eds.) Proceedings of the 31st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a032, pp. 387\u2013395. PMLR, Bejing (2014). https:\/\/proceedings.mlr.press\/v32\/silver14.html"},{"key":"26_CR21","doi-asserted-by":"publisher","unstructured":"Tammewar, A., et al.: Improving the performance of autonomous driving through deep reinforcement learning. Sustainability 15(18) (2023). https:\/\/doi.org\/10.3390\/su151813799, https:\/\/www.mdpi.com\/2071-1050\/15\/18\/13799","DOI":"10.3390\/su151813799"},{"key":"26_CR22","unstructured":"Thrun, S.: Efficient exploration in reinforcement learning. Technical report CMU-CS-92-102, Pittsburgh, PA (1992)"},{"key":"26_CR23","unstructured":"Udugama, B.: Review of deep reinforcement learning for autonomous driving (2023)"},{"key":"26_CR24","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a048, pp. 1995\u20132003. PMLR, New York (2016). https:\/\/proceedings.mlr.press\/v48\/wangf16.html"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (2004). https:\/\/api.semanticscholar.org\/CorpusID:2332513","DOI":"10.1007\/BF00992696"}],"container-title":["Lecture Notes in Networks and Systems","Ambient Intelligence \u2013 Software and Applications \u2013 15th International Symposium on Ambient Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-83117-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T19:18:01Z","timestamp":1740597481000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-83117-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031831164","9783031831171"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-83117-1_26","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"27 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISAmI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Ambient Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salamanca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isaml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isami-conference.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}