{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:42:22Z","timestamp":1782574942689,"version":"3.54.5"},"reference-count":221,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013254","name":"Shandong Province College Students Innovation and Entrepreneurship Training Program","doi-asserted-by":"publisher","award":["S202310435163"],"award-info":[{"award-number":["S202310435163"]}],"id":[{"id":"10.13039\/501100013254","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013254","name":"Shandong Province College Students Innovation and Entrepreneurship Training Program","doi-asserted-by":"publisher","award":["202310435001"],"award-info":[{"award-number":["202310435001"]}],"id":[{"id":"10.13039\/501100013254","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013254","name":"Shandong Province College Students Innovation and Entrepreneurship Training Program","doi-asserted-by":"publisher","award":["S202310435151"],"award-info":[{"award-number":["S202310435151"]}],"id":[{"id":"10.13039\/501100013254","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013254","name":"Shandong Province College Students Innovation and Entrepreneurship Training Program","doi-asserted-by":"publisher","award":["S202310435149"],"award-info":[{"award-number":["S202310435149"]}],"id":[{"id":"10.13039\/501100013254","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013254","name":"Shandong Province College Students Innovation and Entrepreneurship Training Program","doi-asserted-by":"publisher","award":["S202310435032"],"award-info":[{"award-number":["S202310435032"]}],"id":[{"id":"10.13039\/501100013254","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Smart Ocean Ranch Engineering Technology Collaborative Innovation Center; in part by the Research fund for High-Level Talents of Qingdao Agricultural University","award":["1119048"],"award-info":[{"award-number":["1119048"]}]},{"name":"Shandong Agricultural Science and Technology Service Project","award":["2019FW037-4"],"award-info":[{"award-number":["2019FW037-4"]}]},{"name":"Qingdao Science and Technology Demonstration Project - New Modern Agriculture Project in 2024","award":["24-2-8-xdny-11-nsh"],"award-info":[{"award-number":["24-2-8-xdny-11-nsh"]}]},{"name":"Experimental technical project of Qingdao Agricultural University","award":["SYJK18-01"],"award-info":[{"award-number":["SYJK18-01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3479774","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T17:25:51Z","timestamp":1728926751000},"page":"161897-161924","source":"Crossref","is-referenced-by-count":8,"title":["Knowledge Graph Based on Reinforcement Learning: A Survey and New Perspectives"],"prefix":"10.1109","volume":"12","author":[{"given":"Qingfeng","family":"Huo","sequence":"first","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaqiao","family":"Fu","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3897-7629","authenticated-orcid":false,"given":"Caixia","family":"Song","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengmin","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kejia","family":"Qu","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyu","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanqi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajia","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhong","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongwei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Science and Information, Qingdao Agricultural University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Geogle Blog","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636442"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401174"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070843"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2483592"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3447772"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271739"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775250"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00045"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106655"},{"key":"ref14","article-title":"UHop: An unrestricted-hop relation extraction framework for knowledge-based question answering","author":"Chen","year":"2019","journal-title":"arXiv:1904.01246"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00891-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103242"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/3055540.3055549"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290956"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.412"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1299"},{"key":"ref22","article-title":"Leveraging knowledge bases in LSTMs for improving machine reading","author":"Yang","year":"2019","journal-title":"arXiv:1902.09091"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/406"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1282"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.526"},{"key":"ref27","first-page":"1634","article-title":"The role of \u2018condition\u2019 a novel scientific knowledge graph representation and construction model","volume-title":"Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","author":"Jiang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/156"},{"key":"ref29","first-page":"792","article-title":"Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs","volume-title":"Proc. ECAI","author":"Joshi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.14778\/3213880.3213888"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101528"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3059506"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00065"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01175"},{"key":"ref37","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3242997"},{"issue":"1","key":"ref39","first-page":"1","article-title":"A survey on deep reinforcement learning","volume":"41","author":"Liu","year":"2018","journal-title":"Chin. J. Comput. Sci."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/su15031862"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/su15010735"},{"issue":"3","key":"ref42","first-page":"677","article-title":"A novel off policy Q(\u03bb) algorithm based on linear function approximation","volume":"37","author":"Qi-Ming","year":"2024","journal-title":"Chin. J. Comput."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000552"},{"key":"ref47","first-page":"5166","article-title":"Independent policy gradient for large-scale Markov potential games: Sharper rates, function approximation, and game-agnostic convergence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ding"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3264206"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/int.22841"},{"issue":"6","key":"ref50","first-page":"5","article-title":"An end-to-end dialogue system based on medical knowledge graph","volume":"36","author":"Mu","year":"2021","journal-title":"J. Beijing Inf. Sci. Technol. Univ."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.096"},{"issue":"5","key":"ref52","first-page":"488","article-title":"Intelligent ikcommendation method combiiling knowledge graph and Bayesian network","volume":"15","author":"Hou","year":"2020","journal-title":"Joumal CAEIT"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/DSC.2019.00025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.03.014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7519"},{"key":"ref58","volume-title":"Sohu Encyclopedia","year":"2015"},{"key":"ref59","volume-title":"Baidu Encyclopedia","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331203"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1362"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/267"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2021.08.002"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1060"},{"key":"ref65","article-title":"Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning","author":"Das","year":"2017","journal-title":"arXiv:1711.05851"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3233\/SW-160218"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3030076"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1487\/1\/012016"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3028705"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"issue":"3","key":"ref74","first-page":"582","article-title":"Knowledge graph construction techniques","volume":"53","author":"Liu","year":"2016","journal-title":"J. Comput. Res. Develop."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.15888\/j.cnki.csa.006915"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05057-5"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.15439\/2019F3"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.14778\/2732951.2732962"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112948"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671651"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/EIECS53707.2021.9587902"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/AIE57029.2022.00128"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2673243"},{"key":"ref84","article-title":"Knowledge graph representation of typhoon disaster events based on spatiotemporal processes","author":"Wang","year":"2022","journal-title":"J. Geo-information Sci."},{"issue":"4","key":"ref85","first-page":"589","article-title":"Review on knowledge graph techniques","volume":"45","author":"Xu","year":"2016","journal-title":"J. Univ. Electron. Sci. Technol. China"},{"issue":"2","key":"ref86","first-page":"247","article-title":"Knowledge representation learning: A review","volume":"53","author":"Liu","year":"2016","journal-title":"JournaI Comput. Res. Develop."},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC50631.2021.00024"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICETCI55101.2022.9832337"},{"key":"ref89","first-page":"1","article-title":"Knowledge graph construction method of gold mine based on ontology","volume":"24","author":"Zhang","year":"2022","journal-title":"J. Geo-Inf. Sci."},{"issue":"8","key":"ref90","first-page":"424","article-title":"Research on constructing the knowledge graph based on emotional analysis of film review","volume":"37","author":"Xu","year":"2020","journal-title":"Comput. Simul."},{"issue":"2","key":"ref91","first-page":"175","article-title":"Knowledge graph construction techniques: Taxonomy, survey and future directions","volume":"48","author":"Hang","year":"2021","journal-title":"Comput. Sci."},{"issue":"7","key":"ref92","first-page":"1","article-title":"Survey on large scale enterprise\u2014Level knowledge graph practices","volume":"46","author":"Wang","year":"2020","journal-title":"Comput. Eng."},{"issue":"7","key":"ref93","first-page":"79","article-title":"Survey of cyber security knowledge graph","volume":"49","author":"Ding","year":"2021","journal-title":"J. Huazhong Univ. Sci. Technol. Nat. Sci., Ed."},{"issue":"2","key":"ref94","first-page":"227","article-title":"Summary of knowledge graph construction oriented knowledge extraction technology","volume":"21","author":"Yu","year":"2020","journal-title":"J. Inf. Eng. Univ."},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEMT52412.2021.9602840"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-020-00811-0"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3098612"},{"issue":"7","key":"ref98","first-page":"1929","article-title":"Construction techniques and research development of medical knowledge graph","volume":"35","author":"Yuan","year":"2018","journal-title":"Appl. Res. Comput."},{"issue":"12","key":"ref99","first-page":"2585","article-title":"Research review of knowledge graph and its application in medical domain","volume":"55","author":"Hou","year":"2018","journal-title":"J. Comput. Res. Develop."},{"issue":"8","key":"ref100","first-page":"1694","article-title":"Survey of knowledge graph based on reinforcement learning","volume":"59","author":"Ma","year":"2022","journal-title":"J. Comput. Res. Develop."},{"issue":"10","key":"ref101","first-page":"1254","article-title":"Recent advances, key techniques and future challenges of knowledge graph","volume":"42","author":"Ma","year":"2020","journal-title":"Chin. J. Eng."},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892730"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9327031"},{"issue":"6","key":"ref104","first-page":"1969","article-title":"Research progress in knowledge graph and its application in the field of TCM","volume":"22","author":"Sun","year":"2020","journal-title":"Modernization Traditional Chin. Med. Materia Materia-World Sci. Technol."},{"key":"ref105","first-page":"4376","article-title":"A meta-learning knowledge reasoning framework combining semantic path and language model","volume":"44","author":"Duan","year":"2022","journal-title":"J. Electron. Inf. Technol."},{"key":"ref106","article-title":"Design and implementation of the relationship among the characters based on knowledge graph","author":"Feng","year":"2016"},{"key":"ref107","first-page":"74","article-title":"Review of reasoning on knowledge graph","volume":"49","author":"Ma","year":"2022","journal-title":"Comput. Sci."},{"issue":"12","key":"ref108","first-page":"8","article-title":"Survey of knowledge reasoning based on neural network","volume":"55","author":"Zhang","year":"2019","journal-title":"Comput. Eng. Appl."},{"key":"ref109","article-title":"Modern deep reinforcement learning algorithms","author":"Ivanov","year":"2019","journal-title":"arXiv:1906.10025"},{"key":"ref110","volume-title":"Deep Reinforcement Learning Hands-On: Apply Modern RL Methods, With Deep Q-networks, Value Iteration, Policy Gradients, TRPO, AlphaGo Zero and More","author":"Lapan","year":"2018"},{"key":"ref111","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv:1701.07274"},{"key":"ref112","volume-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref113","volume-title":"On-Line Q-Learning Using Connectionist Systems","volume":"37","author":"Rummery","year":"1994"},{"key":"ref114","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref115","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref118","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref119","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.693"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106912"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.10.065"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM49941.2020.9313535"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05532-z"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/JCC56315.2022.00009"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ACAIT53529.2021.9731116"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50496-4_23"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.3390\/make1030048"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6226"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017072"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2925562"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909919"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209979"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01012-6_4"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240863"},{"key":"ref137","article-title":"A tree search algorithm for sequence labeling","author":"Lao","year":"2018","journal-title":"arXiv:1804.10911"},{"key":"ref138","first-page":"324","article-title":"Multi-turn target-guided topic prediction with Monte Carlo tree search","volume-title":"Proc. 18th Int. Conf. Natural Lang. Process. (ICON)","author":"Yang"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC55077.2022.9886718"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967793"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207499"},{"key":"ref142","first-page":"2159","article-title":"Distantly supervised NER with partial annotation learning and reinforcement learning","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Yang"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_27"},{"issue":"4","key":"ref144","first-page":"646","article-title":"A survey on multi-agent hierarchical reinforcement learning","volume":"15","author":"Yin","year":"2020","journal-title":"CAAI Trans. Intell. Syst."},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICICTA49267.2019.00043"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331349"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12063"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1266"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TTHZ.2016.2569460"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2015.2440356"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2016.7498224"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.11.012"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04181-1"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3446428"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3025711"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2018.00135"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref160","article-title":"Hierarchical principles of embodied reinforcement learning: A review","author":"Eppe","year":"2020","journal-title":"arXiv:2012.10147"},{"key":"ref161","first-page":"1","article-title":"Feudal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"5","author":"Dayan"},{"key":"ref162","first-page":"1","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nachum"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref166","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref167","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref168","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref169","article-title":"Distributed deep Q-learning","author":"Yi Ong","year":"2015","journal-title":"arXiv:1508.04186"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3241741"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-3296-1"},{"issue":"2","key":"ref172","first-page":"1895","article-title":"OAGknow: Self-supervised learning for linking knowledge graphs","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80418-3_26"},{"key":"ref174","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3460210.3493563"},{"key":"ref176","first-page":"2300","article-title":"Explainable reinforcement learning: Basic problems exploration and a survey","volume":"34","author":"Xiao","year":"2021","journal-title":"J. Softw."},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015329"},{"key":"ref178","article-title":"Robot representation and reasoning with knowledge from reinforcement learning","author":"Lu","year":"2018","journal-title":"arXiv:1809.11074"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/IHMSC.2019.10156"},{"key":"ref180","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","author":"Singh","year":"2020","journal-title":"arXiv:2011.10024"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1203"},{"key":"ref182","article-title":"Ekar: An explainable method for knowledge aware recommendation","author":"Song","year":"2019","journal-title":"arXiv:1906.09506"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.217"},{"key":"ref184","first-page":"1","article-title":"Reinforcement learning and the reward engineering principle","volume-title":"Proc. AAAI Spring Symp. Ser.","author":"Dewey"},{"key":"ref185","article-title":"Cooperative reasoning on knowledge graph and corpus: A multi-agentreinforcement learning approach","author":"Zhang","year":"2019","journal-title":"arXiv:1912.02206"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"issue":"12","key":"ref187","first-page":"4644","article-title":"Survey of interpretable reasoning on knowledge graphs","volume":"33","author":"Hou","year":"2021","journal-title":"J. Softw."},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00862-z"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11950"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1264"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-82136-4_36"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108843"},{"key":"ref193","first-page":"1","article-title":"Translating embeddings for modeling multi-relational data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Bordes"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1067"},{"key":"ref195","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020","journal-title":"arXiv:2011.00583"},{"key":"ref196","article-title":"Research of dialogue model based on deep learning and reinforcement learning","author":"Cong","year":"2020"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358016"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462859"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2016"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3173355"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557267"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330922"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5301"},{"key":"ref204","first-page":"3720","article-title":"Learning knowledge graph-based world models of textual environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ammanabrolu"},{"key":"ref205","article-title":"Goal-directed story generation: Augmenting generative language models with reinforcement learning","author":"Alabdulkarim","year":"2021","journal-title":"arXiv:2112.08593"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.08.030"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00187"},{"key":"ref208","article-title":"Interpretable disease prediction based on reinforcement path reasoning over knowledge graphs","author":"Sun","year":"2020","journal-title":"arXiv:2010.08300"},{"key":"ref209","article-title":"Training like playing: A reinforcement learning and knowledge graph-based framework for building automatic consultation system in medical field","author":"Huang","year":"2021","journal-title":"arXiv:2106.07502"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005691"},{"key":"ref211","article-title":"A novel deep reinforcement learning based stock direction prediction using knowledge graph and community aware sentiments","author":"Berk Altuner","year":"2021","journal-title":"arXiv:2107.00931"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.3169\/mta.10.8"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06573-8"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCS55155.2022.9846799"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1016\/j.istruc.2022.02.003"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.07.094"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3224228"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107217"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108235"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401171"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-00998-5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10716359.pdf?arnumber=10716359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:46:42Z","timestamp":1732668402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10716359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":221,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3479774","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}