{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:15:44Z","timestamp":1774120544537,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1837135"],"award-info":[{"award-number":["1837135"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NTT Docomo Inc."},{"name":"Swiss National Science Foundation","award":["P400P2_199332"],"award-info":[{"award-number":["P400P2_199332"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539180","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"2913-2923","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-Demand"],"prefix":"10.1145","author":[{"given":"Daniele","family":"Gammelli","sequence":"first","affiliation":[{"name":"Technical University of Denmark, Kgs. Lyngby, Denmark"}]},{"given":"Kaidi","family":"Yang","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"James","family":"Harrison","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team, San Francisco, CA, USA"}]},{"given":"Filipe","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Technical University of Denmark, Kgs. Lyngby , Denmark"}]},{"given":"Francisco","family":"Pereira","sequence":"additional","affiliation":[{"name":"Technical University of Denmark, Kgs. Lyngby , Denmark"}]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"UN Dep. Econ. Soc. Aff. 68% of the world population projected to live in urban areas by 2050 2021. Available at https:\/\/www.un.org\/development\/desa\/en\/news\/ population\/2018-revision-of-world-urbanization-prospects.html."},{"key":"e_1_3_2_2_2_1","volume-title":"Organisation for Economic Co-operation and Development (OECD)","author":"The OECD.","year":"2014","unstructured":"OECD. The cost of air pollution - health impacts of road transport. Technical report, Organisation for Economic Co-operation and Development (OECD), 2014."},{"key":"e_1_3_2_2_3_1","volume-title":"Ridesharing in north america: Past, present, and future. Transport reviews","author":"Chan N. D.","year":"2012","unstructured":"N. D. Chan and S. A. Shaheen. Ridesharing in north america: Past, present, and future. Transport reviews, 2012."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2021.102327"},{"key":"e_1_3_2_2_5_1","volume-title":"Proc. IEEE Int. Conf. on Intelligent Transportation Systems, 2021","author":"Yang K.","year":"2008","unstructured":"K. Yang, M. Tsao, X. Xu, and M. Pavone. Real-time control of mixed fleets in mobility-on-demand systems. In Proc. IEEE Int. Conf. on Intelligent Transportation Systems, 2021. Extended Version, Available at https:\/\/arxiv.org\/abs\/2008.08131."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.05.003"},{"key":"e_1_3_2_2_7_1","volume-title":"Environment and Urban Systems","author":"Levin K.","year":"2017","unstructured":"K. Levin, M.and Kockelman, S. Boyles, and T. Li. A general framework for modeling shared autonomous vehicles with dynamic network-loading and dynamic ride-sharing application. Computers, Environment and Urban Systems, 2017."},{"key":"e_1_3_2_2_8_1","author":"Zhang R.","year":"2016","unstructured":"R. Zhang and M. Pavone. Control of robotic Mobility-on-Demand systems: A queueing-theoretical perspective. Int. Journal of Robotics Research, 2016.","journal-title":"Journal of Robotics Research"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460966"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917533"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00129"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102626"},{"key":"e_1_3_2_2_13_1","volume-title":"Scalable deep reinforcement learning for ride-hailing","author":"Feng J.","year":"2020","unstructured":"J. Feng, M. Gluzman, and J. G. Dai. Scalable deep reinforcement learning for ride-hailing. IEEE Control Systems Letters, 2020."},{"key":"e_1_3_2_2_14_1","volume-title":"A modular and transferable reinforcement learning framework for the fleet rebalancing problem. arXiv preprint arXiv:2105.13284","author":"Skordilis E.","year":"2021","unstructured":"E. Skordilis, Y. Hou, C. Tripp, M. Moniot, P. Graf, and D. Biagioni. A modular and transferable reinforcement learning framework for the fleet rebalancing problem. arXiv preprint arXiv:2105.13284, 2021."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"e_1_3_2_2_16_1","author":"Zardini G.","year":"2021","unstructured":"G. Zardini, N. Lanzetti, M. Pavone, and E. Frazzoli. Analysis and control of autonomous mobility-on-demand systems: A review. Annual Review of Control, Robotics, and Autonomous Systems, 2021. Submitted.","journal-title":"Annual Review of Control, Robotics, and Autonomous Systems"},{"key":"e_1_3_2_2_17_1","volume-title":"Reinforcement learning for ridesharing: A survey. arXiv preprint arXiv:2105.01099","author":"Qin Z.","year":"2021","unstructured":"Z. Qin, H. Zhu, and J. Ye. Reinforcement learning for ridesharing: A survey. arXiv preprint arXiv:2105.01099, 2021."},{"key":"e_1_3_2_2_18_1","author":"Zhang Y.","year":"2022","unstructured":"Y. Zhang, Y. Li, X. Zhou, J. Luo, and Z. Zhang. Urban traffic dynamics prediction-a continuous spatial-temporal meta-learning approach. ACM Transactions on Intelligent Systems and Technology, 2022.","journal-title":"Urban traffic dynamics prediction-a continuous spatial-temporal meta-learning approach. ACM Transactions on Intelligent Systems and Technology"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313577"},{"key":"e_1_3_2_2_20_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018","unstructured":"R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. MIT Press, 2 edition, 2018."},{"key":"e_1_3_2_2_21_1","volume-title":"Int. Conf. on Machine Learning","author":"Finn C.","year":"2017","unstructured":"C. Finn, P. Abbeel, and S. Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In Int. Conf. on Machine Learning, 2017."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/646258.684281"},{"key":"e_1_3_2_2_23_1","volume-title":"Learning to reinforcement learn. arXiv preprint arXiv:1611.05763","author":"Wang J. X.","year":"2016","unstructured":"J. X. Wang, Z. Kurth-Nelson, D. Tirumala, H. Soyer, J. Z Leibo, R. Munos, C. Blundell, D. Kumaran, and M. Botvinick. Learning to reinforcement learn. arXiv preprint arXiv:1611.05763, 2016."},{"key":"e_1_3_2_2_24_1","volume-title":"Rl 2: Fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779","author":"Duan Y.","year":"2016","unstructured":"Y. Duan, J. Schulman, X. Chen, P. L. Bartlett, I. Sutskever, and P. Abbeel. Rl 2: Fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779, 2016."},{"key":"e_1_3_2_2_25_1","volume-title":"Conf. on Neural Information Processing Systems","author":"Battaglia P. W.","year":"2016","unstructured":"P. W. Battaglia, R. Pascanu, M. Lai, D. Rezende, and K. Kavukcuoglu. Interaction networks for learning about objects, relations and physics. In Conf. on Neural Information Processing Systems, 2016."},{"key":"e_1_3_2_2_26_1","volume-title":"Integer programming and combinatorial optimization","author":"Nemhauser G. L","unstructured":"G. L Nemhauser. Integer programming and combinatorial optimization. Springer."},{"key":"e_1_3_2_2_27_1","volume-title":"Recurrent model-free RL is a strong baseline for many POMDPs. arXiv preprint arXiv:2110.05038","author":"Ni T.","year":"2021","unstructured":"T. Ni, B. Eysenbach, and R. Salakhutdinov. Recurrent model-free RL is a strong baseline for many POMDPs. arXiv preprint arXiv:2110.05038, 2021."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102775"},{"key":"e_1_3_2_2_29_1","volume-title":"Int. Conf. on Learning Representations","author":"Mnih V.","year":"2016","unstructured":"V. Mnih, A. Puigdomenech, M. Mirza, A. Graves, T.-P. Lillicrap, T. Harley, D. Silver, and K. Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In Int. Conf. on Learning Representations, 2016."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_2_31_1","volume-title":"et al. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703","author":"Paszke A.","year":"2019","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, et al. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703, 2019."},{"key":"e_1_3_2_2_32_1","volume-title":"IBM ILOG","author":"IBM.","year":"1987","unstructured":"IBM. ILOG CPLEX User's guide. IBM ILOG, 1987."},{"key":"e_1_3_2_2_33_1","volume-title":"Operations Research","author":"Ben-Ayed O.","year":"1990","unstructured":"O. Ben-Ayed and C. Blair. Computational difficulties of bilevel linear programming. Operations Research, 1990."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975994.16"},{"key":"e_1_3_2_2_35_1","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition","author":"Jamal M.","year":"2018","unstructured":"M. Jamal, M. Qi, and M. Shah. Task-agnostic meta-learning for few-shot learning. IEEE Conf. on Computer Vision and Pattern Recognition, 2018."},{"key":"e_1_3_2_2_36_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine S.","year":"2020","unstructured":"S. Levine, A. Kumar, G. Tucker, and J. Fu. Offline reinforcement learning: Tutorial, review, and perspectives on open problems, 2020."},{"key":"e_1_3_2_2_37_1","volume-title":"Crawdad data set epfl\/mobility (v. 2009-02--24)","author":"Piorkowski M.","year":"2009","unstructured":"M. Piorkowski, N. Sarafijanovic-Djukic, and M. Grossglauser. Crawdad data set epfl\/mobility (v. 2009-02--24), 2009."},{"key":"e_1_3_2_2_38_1","volume-title":"Taxi Trip Data","author":"Washington City","year":"2019","unstructured":"City of Washington, DC. Taxi Trip Data, 2019. See https:\/\/opendata.dc.gov\/ documents\/taxi-trips-in-2019\/explore."},{"key":"e_1_3_2_2_39_1","volume-title":"Trip Record Data","author":"NYC Taxi & Limousine Commission","year":"2013","unstructured":"NYC Taxi & Limousine Commission. Trip Record Data, 2013. See https:\/\/www1. nyc.gov\/site\/tlc\/about\/tlc-trip-record-data.page."},{"key":"e_1_3_2_2_40_1","unstructured":"City of Chicago. Taxi Trips 2013. See https:\/\/data.cityofchicago.org\/ Transportation\/Taxi-Trips\/wrvz-psew."},{"key":"e_1_3_2_2_41_1","volume-title":"July","author":"Bracciale L.","year":"2014","unstructured":"L. Bracciale, M. Bonola, P. Loreti, G. Bianchi, R. Amici, and A. Rabuffi. CRAWDAD dataset roma\/taxi (v. 2014-07--17). Downloaded from https:\/\/crawdad.org\/roma\/ taxi\/20140717, July 2014."},{"key":"e_1_3_2_2_42_1","author":"Moreira-Matias L.","year":"2013","unstructured":"L. Moreira-Matias, J. Gama, M. Ferreira, J. Mendes-Moreira, and L. Damas. Predicting taxi--passenger demand using streaming data. IEEE Transactions on Intelligent Transportation Systems, 2013.","journal-title":"Predicting taxi--passenger demand using streaming data. IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2735960.2735985"}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539180","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539180","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:59Z","timestamp":1750186979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539180"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":43,"alternative-id":["10.1145\/3534678.3539180","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539180","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}