{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:37:17Z","timestamp":1772041037189,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,5]],"date-time":"2021-09-05T00:00:00Z","timestamp":1630800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,5]],"date-time":"2021-09-05T00:00:00Z","timestamp":1630800000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,5]],"date-time":"2021-09-05T00:00:00Z","timestamp":1630800000000},"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","award":["62072212"],"award-info":[{"award-number":["62072212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013061","name":"Development Project of Jilin Province of China","doi-asserted-by":"publisher","award":["20200401083GX,2020C003"],"award-info":[{"award-number":["20200401083GX,2020C003"]}],"id":[{"id":"10.13039\/501100013061","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,5]]},"DOI":"10.1109\/iscc53001.2021.9631429","type":"proceedings-article","created":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T20:46:50Z","timestamp":1639601210000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Research and Application of Reinforcement Learning Recommendation Method for Taobao"],"prefix":"10.1109","author":[{"given":"Lan","family":"Huang","sequence":"first","affiliation":[]},{"given":"Xiaofang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xuping","family":"Xie","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","article-title":"Prioritized Experience Replay","author":"schaul","year":"2016","journal-title":"ICLRE"},{"key":"ref31","author":"wang","year":"2016","journal-title":"Sample efficient actor-critic with experience replay"},{"key":"ref30","author":"fortunato","year":"2017","journal-title":"Noisy Networks for Exploration"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742726"},{"key":"ref11","author":"guo","year":"2015","journal-title":"TrustSVD Collaborative Filtering with Both the Explicit and Implicit Influence of User Trust and of Item Ratings"},{"key":"ref12","author":"hu","year":"2018","journal-title":"Reinforcement Learning to Rank in E-Commerce Search Engine Formalization Analysis and Application"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330832"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313404"},{"key":"ref16","article-title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System","author":"chen","year":"2019","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"ref18","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref19","first-page":"1889","article-title":"Trust Region Policy Optimization","volume":"37","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref28","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic algorithms and applications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/192844.192905"},{"key":"ref27","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/245108.245124"},{"key":"ref6","author":"funk","year":"2006","journal-title":"Netflix update Try this at home"},{"key":"ref29","article-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","author":"schulman","year":"2015","journal-title":"Computer ence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.330161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47887-6_34"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"ref1","author":"jussi","year":"1990","journal-title":"An algebra for recommendations using reader data as a basis for measuring document proximity"},{"key":"ref20","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref22","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"hasselt","year":"2015","journal-title":"Computer ence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref24","author":"hessel","year":"2017","journal-title":"Rainbow Combining Improvements in Deep Reinforcement Learning"},{"key":"ref23","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"freitas","year":"2016","journal-title":"ICML"},{"key":"ref26","author":"fujimoto","year":"2018","journal-title":"Addressing Function Approximation Error in Actor-Critic Methods"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"Computer ence"}],"event":{"name":"2021 IEEE Symposium on Computers and Communications (ISCC)","location":"Athens, Greece","start":{"date-parts":[[2021,9,5]]},"end":{"date-parts":[[2021,9,8]]}},"container-title":["2021 IEEE Symposium on Computers and Communications (ISCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9631377\/9631248\/09631429.pdf?arnumber=9631429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:25Z","timestamp":1652201665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9631429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iscc53001.2021.9631429","relation":{},"subject":[],"published":{"date-parts":[[2021,9,5]]}}}