{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T06:05:34Z","timestamp":1780380334871,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":13,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698172","type":"print"},{"value":"9789819698189","type":"electronic"}],"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\/978-981-96-9818-9_43","type":"book-chapter","created":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T12:24:54Z","timestamp":1752927894000},"page":"522-534","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large-Scale Vehicle Navigation Preference Generation Based on Dual Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9670-0673","authenticated-orcid":false,"given":"Yanshu","family":"Shuai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2087-1497","authenticated-orcid":false,"given":"Jiaoling","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1320-8113","authenticated-orcid":false,"given":"Xingyu","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1487-1841","authenticated-orcid":false,"given":"Haoquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"issue":"3","key":"43_CR1","doi-asserted-by":"publisher","first-page":"901","DOI":"10.3934\/jimo.2023108","volume":"20","author":"T Li","year":"2024","unstructured":"Li, T., Wang, N.M., Zhang, M., et al.: Dynamic reversible lane optimization in autonomous driving environments: balancing efficiency and safety. J. Ind. Manage. Optim. 20(3), 901\u2013925 (2024)","journal-title":"J. Ind. Manage. Optim."},{"key":"43_CR2","unstructured":"Calandriello, D., Guo, D., Munos, R., et al.: Human alignment of large language models through online preference optimisation. Comput. Res. Repository (2024)"},{"issue":"2","key":"43_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3054912","volume":"50","author":"A Hussein","year":"2017","unstructured":"Hussein, A., Gaber, M.M., Elyan, E., et al.: Imitation learning: a survey of learning methods. ACM Comput. Surv. 50(2), 1\u201335 (2017)","journal-title":"ACM Comput. Surv."},{"issue":"9","key":"43_CR4","doi-asserted-by":"publisher","first-page":"14128","DOI":"10.1109\/TITS.2022.3144867","volume":"23","author":"L Le Mero","year":"2022","unstructured":"Le Mero, L., Yi, D., Dianati, M., et al.: A survey on imitation learning techniques for end-to-end autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23(9), 14128\u201314147 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"1","key":"43_CR5","doi-asserted-by":"publisher","first-page":"43","DOI":"10.54097\/189b3413","volume":"13","author":"MY Zhou","year":"2024","unstructured":"Zhou, M.Y., Wang, B., Tan, T., et al.: Developing path planning with behavioral cloning and proximal policy optimization for path-tracking and static obstacle nudging. Acad. J. Sci. Technol. 13(1), 43\u201349 (2024)","journal-title":"Acad. J. Sci. Technol."},{"issue":"6","key":"43_CR6","doi-asserted-by":"publisher","first-page":"4307","DOI":"10.1007\/s10462-021-10108-x","volume":"55","author":"S Adams","year":"2022","unstructured":"Adams, S., Cody, T., Beling, P.A.: A survey of inverse reinforcement learning. Artif. Intell. Rev. 55(6), 4307\u20134346 (2022)","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"43_CR7","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/MSP.2020.2988287","volume":"38","author":"T Fernando","year":"2021","unstructured":"Fernando, T., Denman, S., Sridharan, S., et al.: Deep inverse reinforcement learning for behavior prediction in autonomous driving: accurate forecasts of vehicle motion. IEEE Signal Process. Mag. 38(1), 87\u201396 (2021)","journal-title":"IEEE Signal Process. Mag."},{"issue":"5","key":"43_CR8","doi-asserted-by":"publisher","first-page":"3685","DOI":"10.1109\/TITS.2023.3326276","volume":"25","author":"YJ Wang","year":"2024","unstructured":"Wang, Y.J., Niu, Y.C., Zhu, W.Y., et al.: Predicting pedestrian crossing behavior at unsignalized mid-block crosswalks using maximum entropy deep inverse reinforcement learning. IEEE Trans. Intell. Transp. Syst. 25(5), 3685\u20133698 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"43_CR9","unstructured":"Javier, R., Tony, W., Stewart, S., et al.: Open problems and fundamental limitations of reinforcement learning from human feedback. Comput. Res. Repository (2023)"},{"key":"43_CR10","unstructured":"Kaufmann, T., Weng, P., Bengs V., et al.: a survey of reinforcement learning from human feedback. Comput. Res. Repository (2023)"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Cao, Y.L., Ivanovic, B., Xiao, C.W., et al.: Reinforcement learning with human feedback for realistic traffic simulation. Comput. Res. Repository (2024)","DOI":"10.1109\/ICRA57147.2024.10610878"},{"key":"43_CR12","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1127642","author":"MB Hafez","year":"2023","unstructured":"Hafez, M.B., Immisch, T., Weber, T., et al.: Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning. Front. Neurorobot. (2023). https:\/\/doi.org\/10.3389\/fnbot.2023.1127642","journal-title":"Front. Neurorobot."},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lauri\u00e8re, M., Chua, S.J.C., et al.: Population-aware online mirror descent for mean-field games by deep reinforcement learning computing research repository. 2561\u20132563 (2024)","DOI":"10.65109\/VLEY5499"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9818-9_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:49:13Z","timestamp":1780379353000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9818-9_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698172","9789819698189"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9818-9_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}