{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:32:15Z","timestamp":1784392335095,"version":"3.55.0"},"reference-count":93,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/itsc48978.2021.9564924","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:52:26Z","timestamp":1635191546000},"page":"2447-2454","source":"Crossref","is-referenced-by-count":13,"title":["Reinforcement Learning for Ridesharing: A Survey"],"prefix":"10.1109","author":[{"given":"Zhiwei Tony","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongtu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460966"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2020.3014417"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313465"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3027200"},{"key":"ref76","first-page":"577","article-title":"Taxis strike back: A field trial of the driver guidance system","volume":"15","author":"cheng","year":"0","journal-title":"AAMAS'18 Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/609"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487272"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103239"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2529580"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00133"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989167"},{"key":"ref79","article-title":"Nyc taxi & limousine commission trip record data","year":"2020","journal-title":"TLC"},{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00129"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00077"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357799"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357978"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3006084"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3030252"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5388"},{"key":"ref61","article-title":"Learn to earn: Enabling coordination within a ride hailing fleet","author":"chaudhari","year":"0","journal-title":"Proceedings of IEEE International Conference on Big Data"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2934423"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.04.005"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569608"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9111818"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622481"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2931830"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1080.0238"},{"key":"ref67","first-page":"1","article-title":"A distributed model-free ride-sharing algorithm with pricing using deep reinforcement learning","author":"haliem","year":"0","journal-title":"Computer Science in Cars Symposium"},{"key":"ref68","author":"singh","year":"2019","journal-title":"A distributed model-free algorithm for multi-hop ride-sharing using deep reinforcement learning"},{"key":"ref69","author":"haliem","year":"2020","journal-title":"A distributed model-free ride-sharing approach for joint matching pricing and dispatching using deep reinforcement learning"},{"key":"ref2","author":"choi","year":"2020","journal-title":"Uber and Lyft to turn the wheels on car ownership industry experts"},{"key":"ref1","article-title":"MarketsAndMarkets","year":"2018","journal-title":"Ride Sharing Market by Type (E-hailing Station-Based Car Sharing & Rental) Car Sharing (P2P Corporate) Service (Navigation Payment Information) Micro-Mobility (Bicycle Scooter) Vehicle Type and Region - Global Forecast to 2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2020.0960"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref21","article-title":"Automated pricing agents in the on-demand economy","author":"wu","year":"2016","journal-title":"Publisher University of California at Berkeley Berkeley"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330724"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00016"},{"key":"ref26","author":"schulman","year":"2017","journal-title":"Prox-imal policy optimization algorithms"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102829"},{"key":"ref50","article-title":"A deep value-based policy search approach for real-world vehicle repositioning on mobility-on-demand platforms","author":"jiao","year":"0","journal-title":"NeurIPS 2020 Deep Reinforcement Learning Workshop"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.12.005"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2020.07.001"},{"key":"ref92","author":"mehta","year":"2020","journal-title":"Curricu-lum in gradient-based meta-reinforcement learning"},{"key":"ref91","author":"traor\u00e9","year":"2019","journal-title":"Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264535"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485988"},{"key":"ref58","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref57","article-title":"Scalable deep reinforcement learning for ride-hailing","author":"feng","year":"2020","journal-title":"Systems & Control Letters"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102626"},{"key":"ref55","article-title":"Semi-markov reinforcement learning for stochastic resource collection","author":"schmoll","year":"0","journal-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2875524"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2018.12.013"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102738"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/stsy.2019.0037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/inte.2020.1047"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3014076"},{"key":"ref12","article-title":"Dynamic type matching","author":"hu","year":"2020","journal-title":"School of Management Working Paper"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1073\/pnas.1611675114","article-title":"On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment","volume":"114","author":"alonso-mora","year":"0","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref14","author":"shou","year":"2020","journal-title":"Multi-agent reinforcement learning for dynamic routing games A unified paradigm"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume":"703","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref82","year":"2020","journal-title":"Didi gaia open data set Kdd cup 2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COEC.2003.1210269"},{"key":"ref81","year":"2021","journal-title":"UBER Movement"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-29645-X_3"},{"key":"ref84","year":"2021","journal-title":"Didi decision intelligence simulation platform"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3440968.3440975"},{"key":"ref83","author":"qin","year":"2020","journal-title":"KDD Cup 2020 Reinforcement Learning Track"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1800"},{"key":"ref80","year":"2017","journal-title":"Uber pickups in new york city - trip data for over 20 million uber (and other for-hire vehicle) trips in nyc"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"ref4","author":"brown","year":"2020","journal-title":"The Ride-Hail Utopia That Got Stuck in Traffic - WSJ"},{"key":"ref3","author":"smith","year":"2019","journal-title":"Here?s how long you have to wait for an Uber or Lyft in DC"},{"key":"ref6","author":"berner","year":"2019","journal-title":"Dota 2 with large scale deep reinforcement learning"},{"key":"ref5","article-title":"Alphago: Mastering the ancient game of go with machine learning","volume":"9","author":"silver","year":"2016","journal-title":"Research blog"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref8","article-title":"A survey on reinforcement learning models and algorithms for traffic signal control","volume":"50","author":"yau","year":"2017","journal-title":"ACM Comput Surv"},{"key":"ref86","first-page":"10","author":"wu","year":"2017","journal-title":"Flow Architecture and benchmarking for reinforcement learning in traffic control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref87","author":"zhou","year":"2020","journal-title":"Smarts Scalable multi-agent reinforcement learning training school for autonomous driving"},{"key":"ref88","first-page":"1","article-title":"Carla: An open urban driving simulator","author":"dosovitskiy","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21872"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2018.1458984"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220055"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317908"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983379"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411913"},{"key":"ref41","author":"chen","year":"2019","journal-title":"Can sophisticated dispatching strategy acquired by reinforcement learning?-a case study in dynamic courier dispatching system"},{"key":"ref44","article-title":"Augmenting decisions of taxi drivers through reinforcement learning for improving revenues","author":"verma","year":"0","journal-title":"Twenty-Seventh International Conference on Automated Planning and Scheduling"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983689"}],"event":{"name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","location":"Indianapolis, IN, USA","start":{"date-parts":[[2021,9,19]]},"end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564393\/9564395\/09564924.pdf?arnumber=9564924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:32Z","timestamp":1652197652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/itsc48978.2021.9564924","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}