{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:14:48Z","timestamp":1753888488094,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002822","name":"Central South University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002822","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671593","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"5733-5740","source":"Crossref","is-referenced-by-count":4,"title":["A Combinatorial Recommendation System Framework Based on Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Fei","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Biao","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Tianmeng","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Zihan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yilin","family":"Wen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"},{"key":"ref32","article-title":"Deep reinforcement learning for list-wise recommendations","author":"zhao","year":"2017","journal-title":"arXiv preprint arXiv 1801 00257"},{"key":"ref31","first-page":"45","article-title":"Deep learning over multi-field categorical data","author":"zhang","year":"2016","journal-title":"European Conference on Information Retrieval"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1086\/208899"},{"key":"ref12","first-page":"770","article-title":"Webwatcher: A tour guide for the world wide web","author":"joachims","year":"1997","journal-title":"IJCAI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/245108.245126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref16","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref18","article-title":"Deep reinforcement learning based recommendation with explicit user-item interactions modeling","author":"liu","year":"2018","journal-title":"arXiv preprint arXiv 1810 12894"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1282100.1282114"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref28"},{"key":"ref3","article-title":"Neural combinatorial optimization with reinforcement learning","author":"bello","year":"2016","journal-title":"arXiv preprint arXiv 1611 09940"},{"key":"ref27","article-title":"Deep reinforcement learning with attention for slate markov decision processes with high-dimensional states and actions","author":"sunehag","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref6","article-title":"Deep re-inforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref29","article-title":"Rl4rs: A real-world benchmark for reinforcement learning based recommender system","author":"wang","year":"2021","journal-title":"arXiv preprint arXiv 2110 11073"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21512\/comtech.v7i4.3746"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"ref7","article-title":"Learning piece-wise linear models from large scale data for ad click prediction","author":"gai","year":"2017","journal-title":"arXiv preprint arXiv 1704 05194"},{"key":"ref2","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref1","article-title":"Reinforcement learning based recommender systems: A survey","author":"afsar","year":"2021","journal-title":"arXiv preprint arXiv 2101 06286"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1557914.1557930"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2005.115"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref23","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv preprint arXiv 1511 06732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939704"},{"key":"ref25","article-title":"New recommendation system using reinforcement learning","volume":"13","author":"rojanavasu","year":"2005","journal-title":"Special Issue of the Intl J Computer the Internet and Management"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2021,12,15]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671593.pdf?arnumber=9671593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:35Z","timestamp":1652201735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671593","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}