{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:25:24Z","timestamp":1792599924286,"version":"4.5.0"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"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":[[2022,10,8]]},"DOI":"10.1109\/itsc55140.2022.9922205","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:13Z","timestamp":1667526013000},"page":"1342-1349","source":"Crossref","is-referenced-by-count":27,"title":["An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility"],"prefix":"10.1109","author":[{"given":"Lukas M.","family":"Schmidt","sequence":"first","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johanna","family":"Brosig","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Axel","family":"Plinge","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bjoern M.","family":"Eskofier","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Erlangen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Mutschler","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377077"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525901000188"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1080\/00207720500438480"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2777820"},{"key":"ref14","first-page":"92","article-title":"Reward and diversity in multirobot foraging","author":"balch","year":"1999","journal-title":"Work Agents Learning About From and With other Agents"},{"key":"ref53","author":"ge","year":"2017","journal-title":"5g software defined vehicular networks"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575328"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2019.8756984"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.04.012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref19","first-page":"2974","article-title":"Counterfactual multiagent policy gradients","author":"foerster","year":"0","journal-title":"AAAI Conf on Artificial Intelligence"},{"key":"ref18","author":"de witt","year":"2020","journal-title":"Is independent learning all you need in the starcraft multi-agent challenge?"},{"key":"ref51","article-title":"Traffic signal control with reinforcement learning based on region-aware cooperative strategy","author":"wang","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref50","article-title":"Gan and multi-agent DRL based decentralized traffic light signal control","author":"wang","year":"2021","journal-title":"IEEE Trans Veh Technol"},{"key":"ref46","article-title":"Learning to fly-a gym environment with pybullet physics for reinforcement learning of multiagent quadcopter control","author":"panerati","year":"0","journal-title":"IEEE\/RSJ Int Conf on Intelligent Robots and Systems (IROS)"},{"key":"ref45","author":"leurent","year":"2018","journal-title":"An environment for autonomous driving decisionmaking"},{"key":"ref48","article-title":"A cooperative multiagent reinforcement learning framework for resource balancing in complex logistics network","author":"li","year":"0","journal-title":"Proc 3rd Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref47","first-page":"621","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"Int Conf Field Service Robot"},{"key":"ref42","article-title":"SMARTS: scalable multi-agent reinforcement learning training school for autonomous driving","author":"zhou","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341222"},{"key":"ref49","author":"mohanty","year":"2020","journal-title":"Flatland-RL multi-agent reinforcement learning on trains"},{"key":"ref8","article-title":"Multi-agent reinforcement learning: A review of challenges and applications","volume":"11","author":"canese","year":"2021","journal-title":"Journal of Applied Sciences"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref4","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":"ref3","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction Adaptive Computations and Machine Learning"},{"key":"ref6","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"NeurIPS"},{"key":"ref5","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref40","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","author":"zhou","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"papoudakis","year":"2020","journal-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks"},{"key":"ref34","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","author":"liang","year":"0","journal-title":"Int Conf on Machine Learning"},{"key":"ref37","author":"zhou","year":"2021","journal-title":"MALib a parallel framework for population-based multi-agent reinforcement learning"},{"key":"ref36","author":"pretorius","year":"2021","journal-title":"Mava a research framework for distributed multi-agent reinforcement learning"},{"key":"ref31","first-page":"6380","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","author":"gu","year":"2021","journal-title":"Mean-field multi-agent reinforcement learning A decentralized network approach"},{"key":"ref33"},{"key":"ref32","author":"yu","year":"2021","journal-title":"The surprising effectiveness of mappo in cooperative multi -agent games"},{"key":"ref2","author":"mordatch","year":"2017","journal-title":"Emergence of Grounded Compositional Language in Multi-Agent Populations"},{"key":"ref1","author":"oroojlooyjadid","year":"2019","journal-title":"A review of cooperative multiagent deep reinforcement learning"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.11.008"},{"key":"ref24","first-page":"10757","article-title":"Multi-agent determinantal q-learning","author":"yang","year":"0","journal-title":"Int Conf Machine Learning"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2022-Spring54318.2022.9860906"},{"key":"ref23","article-title":"MAVEN: multi-agent variational exploration","author":"mahajan","year":"2019","journal-title":"NeurIPS"},{"key":"ref26","first-page":"7254","article-title":"Learning attentional communication for multiagent cooperation","author":"jiang","year":"2018","journal-title":"NeurIPS"},{"key":"ref25","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467420"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196730"},{"key":"ref22","author":"foerster","year":"2018","journal-title":"QMIX Monotonic value function factorisation for deep multi-agent reinforcement learning"},{"key":"ref65","author":"rietsch","year":"2022","journal-title":"Driver dojo A benchmark for generalizable reinforcement learning for autonomous driving"},{"key":"ref21","first-page":"2085","article-title":"Value-decomposition networks for cooperative multiagent learning based on team reward","author":"sunehag","year":"0","journal-title":"Intl Jnt Conf Autonomous Agents and Multiagent Systems"},{"key":"ref28"},{"key":"ref27","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"singh","year":"2019","journal-title":"Int Conf on Learning Representations"},{"key":"ref29","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume":"12","author":"yang","year":"0","journal-title":"Int Conf on Machine Learning"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref62","article-title":"META: a city-wide taxi repositioning framework based on multi-agent reinforcement learning","author":"liu","year":"2021","journal-title":"IEEE Trans on Intelligent Transportation Systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10050543"}],"event":{"name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","location":"Macau, China","start":{"date-parts":[[2022,10,8]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9921415\/9921739\/09922205.pdf?arnumber=9922205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T22:54:54Z","timestamp":1677538494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9922205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/itsc55140.2022.9922205","relation":{},"subject":[],"published":{"date-parts":[[2022,10,8]]}}}