{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T16:47:34Z","timestamp":1771606054073,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"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":[[2022,6,5]]},"DOI":"10.1109\/iv51971.2022.9827289","type":"proceedings-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:33:28Z","timestamp":1658259208000},"page":"478-483","source":"Crossref","is-referenced-by-count":7,"title":["Social Learning In Markov Games: Empowering Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Xu","family":"Chen","sequence":"first","affiliation":[{"name":"Columbia University,Department of Civil Engineering and Engineering Mechanics,New York,NY,USA,10027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zechu","family":"Li","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Computer Science,New York City,NY,USA,10027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Di","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Civil Engineering and Engineering Mechanics,New York,NY,USA,10027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"Deep reinforcement learning for autonomous driving: A survey","author":"kiran","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref13","first-page":"1610","article-title":"Tunable behaviours in sequential social dilemmas using multi-objective reinforcement learning","author":"o\u2019callaghan","year":"2021","journal-title":"ser AAMAS’21"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref15","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","author":"bowling","year":"2001","journal-title":"Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2"},{"key":"ref16","author":"heinrich","year":"2016","journal-title":"Deep reinforcement learning from self-play in imperfect-information games"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1142\/S0129183119500189"},{"key":"ref4","first-page":"1507","article-title":"Emergence of norms through social learning","author":"sen","year":"2007","journal-title":"Proceedings of the 20th International Joint Conference on Artifical Intelligence ser IJCAI’07"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00262-X"},{"key":"ref6","first-page":"475","article-title":"Emergence of social norms through collective learning in networked agent societies","author":"yu","year":"2013","journal-title":"Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems ser"},{"key":"ref5","first-page":"420","article-title":"Social instruments for robust convention emergence","author":"villatoro","year":"2011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9193-x"},{"key":"ref2","article-title":"A game theoretic approach to norms and agents","author":"boella","year":"2001"},{"key":"ref1","article-title":"Self driving #waymo car tried merging onto the highway, missed multiple opportunities (programmed defensive driving?), then rerouted to exit after failing","year":"2018"},{"key":"ref9","article-title":"Model-free conventions in multi-agent reinforcement learning with heterogeneous p","author":"k\u00f6ster","year":"2020"}],"event":{"name":"2022 IEEE Intelligent Vehicles Symposium (IV)","location":"Aachen, Germany","start":{"date-parts":[[2022,6,4]]},"end":{"date-parts":[[2022,6,9]]}},"container-title":["2022 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9826996\/9826997\/09827289.pdf?arnumber=9827289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T20:03:52Z","timestamp":1659989032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9827289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iv51971.2022.9827289","relation":{},"subject":[],"published":{"date-parts":[[2022,6,5]]}}}