{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:27:17Z","timestamp":1773775637611,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,9,20]],"date-time":"2020-09-20T00:00:00Z","timestamp":1600560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,20]],"date-time":"2020-09-20T00:00:00Z","timestamp":1600560000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,20]],"date-time":"2020-09-20T00:00:00Z","timestamp":1600560000000},"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":[[2020,9,20]]},"DOI":"10.1109\/itsc45102.2020.9294338","type":"proceedings-article","created":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T23:14:55Z","timestamp":1608851695000},"page":"1-6","source":"Crossref","is-referenced-by-count":29,"title":["Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic"],"prefix":"10.1109","author":[{"given":"Maxime","family":"Bouton","sequence":"first","affiliation":[]},{"given":"Alireza","family":"Nakhaei","sequence":"additional","affiliation":[]},{"given":"David","family":"Isele","sequence":"additional","affiliation":[]},{"given":"Kikuo","family":"Fujimura","sequence":"additional","affiliation":[]},{"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref11","article-title":"Can deep reinforcement learning solve Erdos-Selfridge-Spencer games?","author":"raghu","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","author":"lanctot","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793721"},{"key":"ref14","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref15","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Double Q-learning","author":"hasselt","year":"2010","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00239"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1807406.1807449"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.36.1.48"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569729"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147837"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916982"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569316"},{"key":"ref7","first-page":"529","volume":"518","author":"mnih","year":"2015","journal-title":"Human-level control through deep reinforcement learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995818"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593420"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/141000671"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"}],"event":{"name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","location":"Rhodes, Greece","start":{"date-parts":[[2020,9,20]]},"end":{"date-parts":[[2020,9,23]]}},"container-title":["2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9294153\/9294168\/09294338.pdf?arnumber=9294338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T05:31:35Z","timestamp":1670563895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9294338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,20]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/itsc45102.2020.9294338","relation":{},"subject":[],"published":{"date-parts":[[2020,9,20]]}}}