{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:38:05Z","timestamp":1784043485704,"version":"3.55.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197559","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"216-221","source":"Crossref","is-referenced-by-count":18,"title":["Deep Merging: Vehicle Merging Controller Based on Deep Reinforcement Learning with Embedding Network"],"prefix":"10.1109","author":[{"given":"Ippei","family":"Nishitani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalini","family":"Keshavamurthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kentaro","family":"Oguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"399","article-title":"Benchmarks for reinforcement learning inmixed-autonomy traffic","author":"vinitsky","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-005-3808-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_5"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref14","first-page":"1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref15","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"2016","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref16","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI Conf on Artif Intell (AAAI)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317694"},{"key":"ref18","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Symp Oper Syst Design Implementation (OSDI)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2013.6629471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2012.6338779"},{"key":"ref6","first-page":"1","article-title":"Autonomous ramp merge maneuver based on reinforcement learning with continuous action space","author":"wang","year":"2017","journal-title":"IEEE Conf on Intel Transport Syst (ITSC)"},{"key":"ref5","article-title":"Exploring applications of deep reinforcement learning for real-world autonomous driving systems","author":"sobh","year":"2019","journal-title":"Under review for the Int Conf on Comput Vision Theory and Appl (VISAPP)"},{"key":"ref8","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref7","first-page":"57","article-title":"Transfer learning versus multi-agent learning regarding distributed decision-making in highway traffic","volume":"2129","author":"schutera","year":"2018","journal-title":"Agents in Traffic and Transp (ATT)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/01441647.2014.983210"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2011.05.011"},{"key":"ref9","first-page":"2419","article-title":"Learning to navigate in cities without a map","author":"mirowski","year":"2018","journal-title":"Advances in NIPS"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197559.pdf?arnumber=9197559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:54Z","timestamp":1656375114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197559","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}