{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:42:39Z","timestamp":1784212959119,"version":"3.55.0"},"reference-count":151,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tits.2021.3054625","type":"journal-article","created":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T09:55:17Z","timestamp":1612950917000},"page":"4909-4926","source":"Crossref","is-referenced-by-count":1859,"title":["Deep Reinforcement Learning for Autonomous Driving: A Survey"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8641-7530","authenticated-orcid":false,"given":"B Ravi","family":"Kiran","sequence":"first","affiliation":[{"name":"Navya, Courbevoie, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9414-6267","authenticated-orcid":false,"given":"Ibrahim","family":"Sobh","sequence":"additional","affiliation":[{"name":"Valeo Cairo AI Team, Giza, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3259-0052","authenticated-orcid":false,"given":"Victor","family":"Talpaert","sequence":"additional","affiliation":[{"name":"ENSTA Paris, Institut Polytechnique de Paris, Palaiseau Cedex, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7951-878X","authenticated-orcid":false,"given":"Patrick","family":"Mannion","sequence":"additional","affiliation":[{"name":"School of Computer Science, National University of Ireland, Galway, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad A. Al","family":"Sallab","sequence":"additional","affiliation":[{"name":"Navya, Courbevoie, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3755-4245","authenticated-orcid":false,"given":"Senthil","family":"Yogamani","sequence":"additional","affiliation":[{"name":"Valeo Vision Systems, Tuam, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8124-1206","authenticated-orcid":false,"given":"Patrick","family":"Perez","sequence":"additional","affiliation":[{"name":"Valeo.ai, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5220\/0007520300002108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317714"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917447"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569744"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569665"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917178"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917043"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00940"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"ref13","volume-title":"Dimensions Publication Trends","author":"Team","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2012116"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962338"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-2279-5"},{"key":"ref19","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2009"},{"key":"ref20","first-page":"10489","article-title":"Diversity-driven exploration strategy for deep reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Hong","year":"2018"},{"key":"ref21","volume-title":"Reinforcement Learning: State-of-the-Art","author":"van Otterlo","year":"2012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref25","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref26","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. ICML","author":"Silver"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref28","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref30","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref32","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (JMLR)","volume":"70","author":"Haarnoja"},{"key":"ref33","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv:1812.05905"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/153244303765208377"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390278"},{"key":"ref37","article-title":"On-line Q-learning using connectionist systems","author":"Rummery","year":"1994"},{"key":"ref38","volume-title":"Reinforcement Learning an Introduction","author":"Sutton","year":"2018"},{"key":"ref39","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref43","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref45","article-title":"Dueling network architectures for deep reinforcement learning","author":"Wang","year":"2015","journal-title":"arXiv:1511.06581"},{"key":"ref46","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2015","journal-title":"arXiv:1507.06527"},{"key":"ref47","volume-title":"The Behavior of Organisms: An Experimental Analysis","author":"Skinner","year":"1938"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_966"},{"key":"ref49","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"Proc. 15th Int. Conf. Mach. Learn.","author":"Randl\u00f8v"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1209\/epl\/i2000-00208-x"},{"key":"ref51","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. 16th Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref52","first-page":"225","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","volume-title":"Proc. 10th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Devlin"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.090"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754770"},{"key":"ref55","first-page":"1","article-title":"A theoretical and empirical analysis of reward transformations in multi-objective stochastic games","volume-title":"Proc. 16th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Mannion"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-67"},{"key":"ref57","first-page":"1345","article-title":"Multi-objective dynamic dispatch optimisation using multi-agent reinforcement learning","volume-title":"Proc. 15th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Mannion"},{"key":"ref58","first-page":"1","article-title":"Applying multi-agent reinforcement learning to watershed management","volume-title":"Proc. Adapt. Learn. Agents Workshop (AAMAS)","author":"Mason"},{"key":"ref59","volume-title":"Manual Political Economy","author":"Pareto","year":"1906"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09433-x"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref63","article-title":"Decoupling feature extraction from policy learning: Assessing benefits of state representation learning in goal based robotics","author":"Raffin","year":"2019","journal-title":"arXiv:1901.08651"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-015-0356-1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref67","first-page":"2474","article-title":"Policy optimization with demonstrations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref69","article-title":"End-to-end framework for fast learning asynchronous agents","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst., Imitation Learn. Challenges Robot. Workshop (NeurIPS)","author":"Ibrahim"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref71","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","author":"Ng"},{"key":"ref72","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2019.15.AVM-048"},{"key":"ref75","article-title":"A survey of state-action representations for autonomous driving","author":"Leurent","year":"2018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref78","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref79","first-page":"359","article-title":"Urban driving with multi-objective deep reinforcement learning","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Li"},{"key":"ref80","article-title":"Autonomous vehicle control via deep reinforcement learning","author":"Kardell","year":"2017"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref82","first-page":"1","article-title":"End-to-end deep reinforcement learning for lane keeping assist","volume-title":"Proc. MLITS, NIPS Workshop","volume":"2","author":"Sallab"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317735"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2106158"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref88","article-title":"Reinforcement learning with A* and a deep heuristic","author":"Keselman","year":"2018","journal-title":"arXiv:1811.07745"},{"key":"ref89","article-title":"INTERACTION dataset: An INTERnational, adversarial and cooperative moTION dataset in interactive driving scenarios with semantic maps","author":"Zhan","year":"2019","journal-title":"arXiv:1910.03088"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref91","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Watter"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.12.271"},{"key":"ref93","first-page":"1","article-title":"Recurrent environment simulators","volume-title":"Proc. 5th Int. Conf. Learn. Represent., ICLR","author":"Chiappa"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref95","first-page":"1800","article-title":"Simple random search of static linear policies is competitive for reinforcement learning","volume-title":"Proc. 31st Annu. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Mania"},{"key":"ref96","volume-title":"Torcs, the Open Racing Car Simulator","author":"Wymann","year":"2000"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref100","volume-title":"Deepdrive\/Deepdrive: 2.0","author":"Quiter","year":"2018"},{"key":"ref101","volume-title":"Drive Constellation Now Available","year":"2019"},{"key":"ref102","volume-title":"Multi-Agent Autonomous Driving Simulator Built on Top of TORCS","author":"Santara","year":"2019"},{"key":"ref103","article-title":"Flow: Architecture and benchmarking for reinforcement learning in traffic control","author":"Wu","year":"2017","journal-title":"arXiv:1710.05465"},{"key":"ref104","volume-title":"A Collection of Environments for Autonomous Driving and Tactical Decision-Making Tasks","author":"Leurent","year":"2019"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3390\/s19030648"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907423"},{"key":"ref107","volume-title":"Carla Autonomous Driving Challenge","author":"German Ros","year":"2019"},{"key":"ref108","article-title":"Pre-crash scenario typology for crash avoidance research","author":"Najm","year":"2007"},{"key":"ref109","first-page":"1","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pomerleau"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref111","first-page":"1","article-title":"End to end learning for self-driving cars","volume-title":"Proc. NIPS Deep Learn. Symp.","author":"Bojarski"},{"key":"ref112","article-title":"Explaining how a deep neural network trained with End-to-End learning steers a car","author":"Bojarski","year":"2017","journal-title":"arXiv:1704.07911"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref114","first-page":"1","article-title":"Learning to drive using inverse reinforcement learning and deep Q-networks","volume-title":"Proc. NIPS Workshops","author":"Sharifzadeh"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793740"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793668"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894216"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317839"},{"key":"ref123","first-page":"1","article-title":"Sample efficient actor-critic with experience replay","volume-title":"Proc. 5th Int. Conf. Learn. Represent., ICLR","author":"Wang"},{"key":"ref124","article-title":"Composing meta-policies for autonomous driving using hierarchical deep reinforcement learning","author":"Liaw","year":"2017","journal-title":"arXiv:1711.01503"},{"key":"ref125","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref126","article-title":"Transferring autonomous driving knowledge on simulated and real intersections","volume-title":"Proc. Lifelong Learn., Reinforcement Learn. Approach, ICML Workshop (NeurIPS)","author":"Isele"},{"key":"ref127","article-title":"Learning to reinforcement learn","volume-title":"Proc. Complete CogSci","author":"Wang"},{"key":"ref128","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref129","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref130","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref131","first-page":"1","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","volume-title":"Proc. 6th Int. Conf. Learn. Represent., ICLR","author":"Al-Shedivat"},{"key":"ref132","first-page":"1","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ha"},{"key":"ref133","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00284"},{"key":"ref136","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chentanez"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref138","article-title":"Large-scale study of curiosity-driven learning","author":"Burda","year":"2018","journal-title":"arXiv:1808.04355"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"ref140","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv:1610.03295"},{"key":"ref141","article-title":"Combining deep reinforcement learning and safety based control for autonomous driving","author":"Xiong","year":"2016","journal-title":"arXiv:1612.00147"},{"issue":"1","key":"ref142","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/832"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2893683"},{"key":"ref147","volume-title":"OpenAI Baselines","author":"Dhariwal","year":"2017"},{"key":"ref148","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2018","journal-title":"arXiv:1809.02627"},{"key":"ref149","volume-title":"TF-Agents: A Library for Reinforcement Learning in Tensorflow","author":"Guadarrama","year":"2018"},{"key":"ref150","article-title":"Rlpyt: A research code base for deep reinforcement learning in PyTorch","author":"Stooke","year":"2019","journal-title":"arXiv:1909.01500"},{"key":"ref151","article-title":"Behaviour suite for reinforcement learning","author":"Osband","year":"2019","journal-title":"arXiv:1908.03568"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9784950\/09351818.pdf?arnumber=9351818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:56:02Z","timestamp":1704844562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9351818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":151,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2021.3054625","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}