{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:22:43Z","timestamp":1783426963552,"version":"3.54.6"},"reference-count":19,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671687","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T15:39:16Z","timestamp":1642088356000},"page":"5703-5707","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning based Recommender System with State Representation"],"prefix":"10.1109","author":[{"given":"Peng","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"ref12","article-title":"Deep reinforcement learning in large discrete action spaces[J]","author":"dulac-arnold","year":"2015"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning[J]","author":"lillicrap","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref15","article-title":"Deep reinforcement learning based recommendation with explicit user-item interactions modeling","author":"liu","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/AIAM48774.2019.00011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning[J]","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref19","article-title":"RL4RS: A Real-World Benchmark for Reinforcement Learning based Recommender System [J]","author":"wang","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1297231.1297250"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1089551.1089606"},{"key":"ref6","article-title":"Dj-mc: A reinforcement learning agent for music playlist recommendation","author":"liebman","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10257-013-0222-3"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning[C]","volume":"30","author":"van hasselt","year":"2016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref7","article-title":"Deep reinforcement learning for sepsis treatment","author":"raghu","year":"2017"},{"key":"ref2","first-page":"770","article-title":"Webwatcher: A tour guide for the world wide web","author":"joachims","year":"1997","journal-title":"IJCAI"},{"key":"ref1","volume":"2","author":"sutton","year":"2017","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref9","article-title":"Prioritized experience replay[J]","author":"schaul","year":"2015"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,15]]},"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\/09671687.pdf?arnumber=9671687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T17:05:49Z","timestamp":1674407149000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671687","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}