{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T08:11:06Z","timestamp":1780992666878,"version":"3.54.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319715889","type":"print"},{"value":"9783319715896","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-71589-6_36","type":"book-chapter","created":{"date-parts":[[2017,12,28]],"date-time":"2017-12-28T19:13:18Z","timestamp":1514488398000},"page":"417-429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Survival-Oriented Reinforcement Learning Model: An Effcient and Robust Deep Reinforcement Learning Algorithm for Autonomous Driving Problem"],"prefix":"10.1007","author":[{"given":"Changkun","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaodi","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,12,29]]},"reference":[{"issue":"7540","key":"36_CR1","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"36_CR2","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"36_CR3","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning, arXiv preprint arXiv:1509.02971 (2015)"},{"key":"36_CR4","unstructured":"Heess, N., Hunt, J.J., Lillicrap, T.P., Silver, D.: Memory-based control with recurrent neural networks, arXiv preprint arXiv:1512.04455 (2015)"},{"key":"36_CR5","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"36_CR6","unstructured":"Shalev-Shwartz, S., Shammah, S., Shashua, A.: Safe, multi-agent, reinforcement learning for autonomous driving, arXiv preprint arXiv:1610.03295 (2016)"},{"key":"36_CR7","unstructured":"Sallab, A.E., Abdou, M., Perot, E., Yogamani, S.: End-to-end deep reinforcement learning for lane keeping assist, arXiv preprint arXiv:1612.04340 (2016)"},{"issue":"7626","key":"36_CR8","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwi\u0144ska, A., Colmenarejo, S.G., Grefenstette, E., Ramalho, T., Agapiou, J., et al.: Hybrid computing using a neural network with dynamic external memory. Nature 538(7626), 471\u2013476 (2016)","journal-title":"Nature"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 1. ACM (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"36_CR10","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, pp. 4565\u20134573 (2016)"},{"key":"36_CR11","unstructured":"Laroche, R., Fatemi, M., Romoff, J., van Seijen, H.: Multi-advisor reinforcement learning, arXiv preprint arXiv:1704.00756 (2017)"},{"key":"36_CR12","unstructured":"Zhan, Y., Ammar, H.B., et al.: Theoretically-grounded policy advice from multiple teachers in reinforcement learning settings with applications to negative transfer (2016)"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Hester, T., Vecerik, M., Pietquin, O., Lanctot, M., Schaul, T., Piot, B., Sendonaris, A., Dulac-Arnold, G., Osband, I., Agapiou, J., et al.: Learning from demonstrations for real world reinforcement learning, arXiv preprint arXiv:1704.03732 (2017)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"36_CR14","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"1999","unstructured":"Altman, E.: Constrained Markov Decision Processes, vol. 7. CRC Press, Boca Raton (1999)"},{"issue":"3","key":"36_CR15","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.sysconle.2004.08.007","volume":"54","author":"VS Borkar","year":"2005","unstructured":"Borkar, V.S.: An actor-critic algorithm for constrained Markov decision processes. Syst. Control Lett. 54(3), 207\u2013213 (2005)","journal-title":"Syst. Control Lett."},{"key":"36_CR16","unstructured":"Chow, Y., Ghavamzadeh, M., Janson, L., Pavone, M.: Risk-constrained reinforcement learning with percentile risk criteria, arXiv preprint arXiv:1512.01629 (2015)"},{"key":"36_CR17","unstructured":"Loiacono, D., Cardamone, L., Lanzi, P.L.: Simulated car racing championship: competition software manual, arXiv preprint arXiv:1304.1672 (2013)"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-71589-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T12:59:34Z","timestamp":1660222774000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-71589-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319715889","9783319715896"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-71589-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"29 December 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/10times.com\/icig-sa","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}