{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:24Z","timestamp":1750220484094,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T00:00:00Z","timestamp":1634860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,22]]},"DOI":"10.1145\/3501409.3501570","type":"proceedings-article","created":{"date-parts":[[2022,1,2]],"date-time":"2022-01-02T06:18:12Z","timestamp":1641104292000},"page":"889-894","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Application Research of end to end behavior decision based on deep reinforcement learning"],"prefix":"10.1145","author":[{"given":"Xiao","family":"wenwen","sequence":"first","affiliation":[{"name":"School of computer science and Engineering, Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,12,31]]},"reference":[{"issue":"5","key":"e_1_3_2_1_1_1","first-page":"289","article-title":"A summary of worldwide intelligent vehicle","volume":"23","author":"Xu Y C","year":"2001","unstructured":"Xu Y C, Wang R B, Li B and Li B.2001.A summary of worldwide intelligent vehicle. Automotive Engineering, 23 (5):289--295.","journal-title":"Automotive Engineering"},{"key":"e_1_3_2_1_2_1","volume-title":"Re-search on behavior decision-making system for unmanned vehicle. Automobile Technology","author":"Lu","year":"2018","unstructured":"XIONG Lu, KANG Yu-chen, ZHANG Pei-zhi, et al. Re-search on behavior decision-making system for unmanned vehicle. Automobile Technology. 2018, 515(08):1--9."},{"key":"e_1_3_2_1_3_1","volume-title":"Acta Electronica Sinica","author":"Guo","year":"2013","unstructured":"LIU Guo-rong, ZHANG Yang-ming. Trajectory tracking of mobile robots based on fuzzy PID-P type iterative learning control. Acta Electronica Sinica, 2013, 41(8):1536--1541."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.11834\/jig.200428"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1109\/TIV.2016.2578706]"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.2307\/2531839]"},{"key":"e_1_3_2_1_7_1","volume-title":"Mach Learn","author":"Hafner R","year":"2011","unstructured":"Hafner R, Riedmiller M, Reinforment learning in feedback control. Mach Learn, 2011, 84(1-2):137--169."},{"unstructured":"John Schulman Filip Wolski et al. Proximal Policy Optimization Algorithms. arXiv preprint arXiv:1707.06347.2017.","key":"e_1_3_2_1_8_1"},{"unstructured":"Tuomas Haarnoja Aurick Zhou et al. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor arXiv preprint arXiv:1801.01290.2018.","key":"e_1_3_2_1_9_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_11_1","volume-title":"Adri\u00e0 Puigdom\u00e8nech Badia, et al. Asynchronous Methods for Deep Reinforcement Learning arXiv preprint arXiv:1602.01783","author":"Volodymyr Mnih","year":"2016","unstructured":"Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8nech Badia, et al. Asynchronous Methods for Deep Reinforcement Learning arXiv preprint arXiv:1602.01783, 2016."},{"key":"e_1_3_2_1_12_1","volume-title":"Continuous control with deep reinforcement learning arXiv preprint arXiv:1509.02971","author":"Timothy P.","year":"2015","unstructured":"Timothy P. Lillicrap, Jonathan J. Hunt, Continuous control with deep reinforcement learning arXiv preprint arXiv:1509.02971, 2015."},{"unstructured":"Juliani A. Berges V Teng E Cohen A Harper J Elion C Goy C Gao Y Henry H Mattar M. Lange D. (2020). Unity: A General Platform for Intelligent Agents. arXiv preprint arXiv:1809.02627. https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/Unity-Technologies\/ml-agents.","key":"e_1_3_2_1_13_1"}],"event":{"acronym":"EITCE 2021","name":"EITCE 2021: 2021 5th International Conference on Electronic Information Technology and Computer Engineering","location":"Xiamen China"},"container-title":["Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3501409.3501570","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3501409.3501570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:02Z","timestamp":1750193342000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3501409.3501570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,22]]},"references-count":13,"alternative-id":["10.1145\/3501409.3501570","10.1145\/3501409"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3501409.3501570","relation":{},"subject":[],"published":{"date-parts":[[2021,10,22]]},"assertion":[{"value":"2021-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}