{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:07:24Z","timestamp":1782756444172,"version":"3.54.5"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Equipment Comprehensive Research Project","award":["424[2021]"],"award-info":[{"award-number":["424[2021]"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871405"],"award-info":[{"award-number":["61871405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3213649","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T16:08:36Z","timestamp":1665418116000},"page":"108785-108796","source":"Crossref","is-referenced-by-count":20,"title":["A Deep Reinforcement Learning-Based Geographic Packet Routing Optimization"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8739-2454","authenticated-orcid":false,"given":"Yijie","family":"Bai","sequence":"first","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daojie","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengxiang","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, Luoyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuntian","family":"Lei","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhoutai","family":"Tian","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420040401.ch12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14257\/ijgdc.2016.9.2.21"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-820488-7.00031-1"},{"issue":"7","key":"ref4","first-page":"665","article-title":"Reinforcement learning","volume":"15","author":"Sutton","year":"1998","journal-title":"Bradford Book"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref7","first-page":"6","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Boyan"},{"key":"ref8","article-title":"Predictive Q-routing: A memory-based reinforcement learning approach to adaptive traffic control","volume-title":"Neural Information Processing Systems","author":"Choi","year":"1995"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/crowncom.2009.5189189"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2021.103181"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3074015"},{"key":"ref12","article-title":"A deep-reinforcement learning approach for software-defined networking routing optimization","author":"Stampa","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CompComm.2018.8780798"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877686"},{"key":"ref15","article-title":"ENERO: Efficient real-time WAN routing optimization with deep reinforcement learning","author":"Almasan","year":"2021","journal-title":"arXiv:2109.10883"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144110"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/345910.345953"},{"key":"ref20","article-title":"An overview of position based routing protocols","author":"Shringi","year":"2019"},{"key":"ref21","first-page":"12","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21937-5_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(80)90066-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/2412323"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref27","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/bf01386390"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/23\/18\/015"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09915566.pdf?arnumber=9915566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:00:17Z","timestamp":1769493617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9915566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3213649","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}