{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:26:37Z","timestamp":1772303197505,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1109\/smc52423.2021.9658943","type":"proceedings-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:34:35Z","timestamp":1641501275000},"page":"1691-1698","source":"Crossref","is-referenced-by-count":11,"title":["Online Multimodal Transportation Planning using Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Amirreza","family":"Farahani","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology,Department of Industrial Engineering,Eindhoven,The Netherlands,5612 AZ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Genga","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,Department of Industrial Engineering,Eindhoven,The Netherlands,5612 AZ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Remco","family":"Dijkman","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,Department of Industrial Engineering,Eindhoven,The Netherlands,5612 AZ"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24455-1_33"},{"key":"ref31","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s12599-019-00583-6"},{"key":"ref34","first-page":"1067","article-title":"he Bellman equation for minimizing the maximum cost. Nonlinear Analysis: Theory","volume":"13","author":"barron","year":"1989","journal-title":"Methods and Applications"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/su11092577"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2019.09.014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2020.102161"},{"key":"ref13","first-page":"9839","article-title":"Reinforcement learning for solving the vehicle routing problem","author":"nazari","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","author":"applegate","year":"2006","journal-title":"The Traveling Salesman Problem A Computational Study"},{"key":"ref15","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Proceedings of the 29th Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref16","article-title":"Neural combinatorial optimization with reinforcement learning","author":"bello","year":"2017","journal-title":"ICLR (Workshop)"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"6348","article-title":"Learning combinatorial optimization algorithms over graphs","author":"khalil","year":"2017","journal-title":"proceedings of the 31st Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93031-2_12"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2015.02.020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37494-5_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2016.06.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5220\/0007395502560265"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/0305215X.2016.1190351"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2015.09.007"},{"key":"ref29","article-title":"Using Reinforcement Learning for a Large Variable-Dimensional Inventory Management Problem","author":"meisheri","year":"2020","journal-title":"Adaptive Learning Agents Workshop at AAMAS"},{"key":"ref8","first-page":"176","article-title":"Anticipatory Scheduling of Freight in a Synchromodal Transportation Network. Transp. Res. Part E: Logist","volume":"105","author":"rivera","year":"2017","journal-title":"Transp Rev"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2016.10.001"},{"key":"ref2","first-page":"547","article-title":"Multi-objective optimization of multimodal passenger transportation networks: coping with demand uncertainty","author":"brands","year":"2014","journal-title":"Proc of 1st International Conference on Engineering and Applied Sciences"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2012.03.010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/8645793"},{"key":"ref20","article-title":"Attention, learn to solve routing problems!","author":"kool","year":"2019","journal-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)"},{"key":"ref22","article-title":"A hybrid of deep reinforcement learning and local search for the vehicle routing problems","author":"zhao","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref21","first-page":"465","article-title":"Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning","author":"da costa","year":"2020","journal-title":"Asian Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2018.1535205"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASMC.2018.8373191"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.07.004"},{"key":"ref25","article-title":"A Reinforcement Learning Approach to Robust Scheduling of Semiconductor Manufacturing Facilities","author":"park","year":"2019","journal-title":"IEEE Transactions on Automation Science and Engineering"}],"event":{"name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Melbourne, Australia","start":{"date-parts":[[2021,10,17]]},"end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658572\/9658575\/09658943.pdf?arnumber=9658943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T21:23:20Z","timestamp":1656365000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9658943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/smc52423.2021.9658943","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}