{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:57:07Z","timestamp":1775109427908,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8593725","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"3640-3647","source":"Crossref","is-referenced-by-count":17,"title":["Game-Theoretic Cooperative Lane Changing Using Data-Driven Models"],"prefix":"10.1109","author":[{"given":"Guohui","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sina","family":"Aghli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoffer","family":"Heckman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"hessel","year":"2017","journal-title":"Rainbow Combining Improvements in Deep Reinforcement Learning"},{"key":"ref38","author":"wang","year":"2015","journal-title":"Dueling network architectures for deep reinforcement learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"},{"key":"ref32","author":"filar","year":"2012","journal-title":"Competitive Markov Decision Processes"},{"key":"ref31","first-page":"149","article-title":"A data-driven model for lane-changing in traffic simulation","author":"bi","year":"2016","journal-title":"Symposium on Computer Animation"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3141\/1857-04"},{"key":"ref37","first-page":"5","article-title":"Deep reinforcement learning with double q-learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460691"},{"key":"ref34","article-title":"Bullet physics engine","volume":"1","author":"coumans","year":"2010","journal-title":"Open Source Software"},{"key":"ref10","author":"foerster","year":"2017","journal-title":"Counterfactual multi-agent policy gradients"},{"key":"ref40","first-page":"89","article-title":"Convergence problems of general-sum multiagent rein-forcement learning","author":"bowling","year":"2000","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref12","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","volume":"98","author":"hu","year":"1998","journal-title":"ICML"},{"key":"ref13","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"le cun","year":"2015","journal-title":"Nature"},{"key":"ref15","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":"ref16","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref28","author":"schulman","year":"2016","journal-title":"Optimizing expectations From deep reinforcement learning to stochastic computation graphs"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(02)00026-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/35\/15\/302"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2005.11.016"},{"key":"ref5","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1613\/jair.2447","article-title":"Optimal and approximate q-value functions for decentralized pomdps","volume":"32","author":"oliehoek","year":"2008","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2005.04.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0191-2607(91)90015-I"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref22","author":"lowe","year":"2017","journal-title":"Multi-agent actor-critic for mixed cooperative-competitive environments"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref24","article-title":"Cooperative multiagent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2017)"},{"key":"ref23","author":"usunier","year":"2016","journal-title":"Episodic exploration for deep deterministic policies An application to starcraft micromanagement tasks"},{"key":"ref26","first-page":"4193","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","author":"lanctot","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","author":"mordatch","year":"2017","journal-title":"Emergence of Grounded Compositional Language in Multi-Agent Populations"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08593725.pdf?arnumber=8593725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:51:34Z","timestamp":1598248294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8593725\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8593725","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}