{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T14:59:20Z","timestamp":1777301960589,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,8,15]],"date-time":"2018-08-15T00:00:00Z","timestamp":1534291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF CAREER grant","award":["IIS-1553687"],"award-info":[{"award-number":["IIS-1553687"]}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CMMI-1434401"],"award-info":[{"award-number":["CMMI-1434401"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1423056"],"award-info":[{"award-number":["IIS-1423056"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1405985"],"award-info":[{"award-number":["CNS-1405985"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1718853"],"award-info":[{"award-number":["IIS-1718853"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,8,15]]},"DOI":"10.1145\/3233547.3233554","type":"proceedings-article","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T12:05:17Z","timestamp":1535112317000},"page":"492-501","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Robust Actor-Critic Contextual Bandit for Mobile Health (mHealth) Interventions"],"prefix":"10.1145","author":[{"given":"Feiyun","family":"Zhu","sequence":"first","affiliation":[{"name":"The University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyu","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington; Tencent AI Lab, Arlington, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,8,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Harnessing different motivational frames via mobile phones to promote daily physical activity and reduce sedentary behavior in aging adults. Plos ONE 8, 4","author":"Abby King","year":"2013","unstructured":"King Abby , Hekler Eric , Grieco Lauren , Winter Sandra , Sheats Jylana , Buman Matthew , .., and Cirimele Jesse . 2013. Harnessing different motivational frames via mobile phones to promote daily physical activity and reduce sedentary behavior in aging adults. Plos ONE 8, 4 ( 2013 ). King Abby, Hekler Eric, Grieco Lauren, Winter Sandra, Sheats Jylana, Buman Matthew, .., and Cirimele Jesse. 2013. Harnessing different motivational frames via mobile phones to promote daily physical activity and reduce sedentary behavior in aging adults. Plos ONE 8, 4 (2013)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10488-012-0424-x"},{"key":"e_1_3_2_1_3_1","volume-title":"Pseudoreward Algorithms for Contextual Bandits with Linear Payoff Functions. In JMLR: Workshop and Conference Proceedings. 1--19","author":"Chou Ku-Chun","year":"2014","unstructured":"Ku-Chun Chou , Hsuan-Tien Lin , Chao-Kai Chiang , and Chi-Jen Lu . 2014 . Pseudoreward Algorithms for Contextual Bandits with Linear Payoff Functions. In JMLR: Workshop and Conference Proceedings. 1--19 . Ku-Chun Chou, Hsuan-Tien Lin, Chao-Kai Chiang, and Chi-Jen Lu. 2014. Pseudoreward Algorithms for Contextual Bandits with Linear Payoff Functions. In JMLR: Workshop and Conference Proceedings. 1--19."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/10691898.2011.11889610"},{"key":"e_1_3_2_1_5_1","first-page":"6","article-title":"Randomised trials for the Fitbit generation","volume":"12","author":"Dempsey Walter","year":"2016","unstructured":"Walter Dempsey , Peng Liao , Pedja Klasnja , Inbal Nahum-Shani , and Susan A. Murphy . 2016 . Randomised trials for the Fitbit generation . Significance 12 , 6 (Dec 2016), 20 -- 23. Walter Dempsey, Peng Liao, Pedja Klasnja, Inbal Nahum-Shani, and Susan A. Murphy. 2016. Randomised trials for the Fitbit generation. Significance 12, 6 (Dec 2016), 20 -- 23.","journal-title":"Significance"},{"key":"e_1_3_2_1_6_1","unstructured":"Lee Dicker. 2014. Sparsity and the truncated l- 2-norm. In Artificial Intelligence and Statistics. 159--166.  Lee Dicker. 2014. Sparsity and the truncated l- 2-norm. In Artificial Intelligence and Statistics. 159--166."},{"key":"e_1_3_2_1_7_1","unstructured":"Miroslav Dud\u00edk John Langford and Lihong Li. 2011. Doubly Robust Policy Evaluation and Learning. In ICML. 1097--1104.   Miroslav Dud\u00edk John Langford and Lihong Li. 2011. Doubly Robust Policy Evaluation and Learning. In ICML. 1097--1104."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2016.05.002"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806568"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2013.4642"},{"key":"e_1_3_2_1_12_1","volume-title":"AAAI Workshop: Computer Poker and Imperfect Information.","author":"Ho Chun-Yen","year":"2015","unstructured":"Chun-Yen Ho and Hsuan-Tien Lin . 2015 . Contract Bridge Bidding by Learning .. In AAAI Workshop: Computer Poker and Imperfect Information. Chun-Yen Ho and Hsuan-Tien Lin. 2015. Contract Bridge Bidding by Learning.. In AAAI Workshop: Computer Poker and Imperfect Information."},{"key":"e_1_3_2_1_13_1","unstructured":"Wenhao Jiang Feiping Nie and Heng Huang. 2015. Robust Dictionary Learning with Capped l1-Norm.. In IJCAI. 3590--3596.   Wenhao Jiang Feiping Nie and Heng Huang. 2015. Robust Dictionary Learning with Capped l1-Norm.. In IJCAI. 3590--3596."},{"key":"e_1_3_2_1_14_1","volume-title":"S","author":"Klasnja Predrag","year":"2015","unstructured":"Predrag Klasnja , Eric B Hekler , Saul Shiffman , Audrey Boruvka , Daniel Almirall , Ambuj Tewari , and Susan A Murphy . 2015. Microrandomized trials: An experimental design for developing just-in-time adaptive interventions. Health Psychology 34 , S ( 2015 ), 1220. Predrag Klasnja, Eric B Hekler, Saul Shiffman, Audrey Boruvka, Daniel Almirall, Ambuj Tewari, and Susan A Murphy. 2015. Microrandomized trials: An experimental design for developing just-in-time adaptive interventions. Health Psychology 34, S (2015), 1220."},{"key":"e_1_3_2_1_15_1","first-page":"1107","article-title":"Least-squares policy iteration","author":"Lagoudakis Michail G","year":"2003","unstructured":"Michail G Lagoudakis and Ronald Parr . 2003 . Least-squares policy iteration . Journal of machine learning research 4 , Dec (2003), 1107 -- 1149 . Michail G Lagoudakis and Ronald Parr. 2003. Least-squares policy iteration. Journal of machine learning research 4, Dec (2003), 1107--1149.","journal-title":"Journal of machine learning research 4"},{"key":"e_1_3_2_1_17_1","volume-title":"NIPS 2014 Workshop: Personalization: Methods and Applications. 1 -- 9.","author":"Lei Huitian","year":"2014","unstructured":"Huitian Lei , A. Tewari , and Susan Murphy . 2014 . An Actor-Critic Contextual Bandit Algorithm for Personalized Interventions using Mobile Devices . In NIPS 2014 Workshop: Personalization: Methods and Applications. 1 -- 9. Huitian Lei, A. Tewari, and Susan Murphy. 2014. An Actor-Critic Contextual Bandit Algorithm for Personalized Interventions using Mobile Devices. In NIPS 2014 Workshop: Personalization: Methods and Applications. 1 -- 9."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28194-0_15"},{"key":"e_1_3_2_1_20_1","volume-title":"Adaptive Graph Convolutional Neural Networks. arXiv:1801.03226","author":"Li Ruoyu","year":"2018","unstructured":"Ruoyu Li , Sheng Wang , Feiyun Zhu , and Junzhou Huang . 2018. Adaptive Graph Convolutional Neural Networks. arXiv:1801.03226 ( 2018 ). Ruoyu Li, Sheng Wang, Feiyun Zhu, and Junzhou Huang. 2018. Adaptive Graph Convolutional Neural Networks. arXiv:1801.03226 (2018)."},{"key":"e_1_3_2_1_21_1","volume-title":"Recurrent reinforcement learning: a hybrid approach. arXiv:1509.03044","author":"Li Xiujun","year":"2015","unstructured":"Xiujun Li , Lihong Li , Jianfeng Gao , Xiaodong He , Jianshu Chen , Li Deng , and Ji He. 2015. Recurrent reinforcement learning: a hybrid approach. arXiv:1509.03044 ( 2015 ). Xiujun Li, Lihong Li, Jianfeng Gao, Xiaodong He, Jianshu Chen, Li Deng, and Ji He. 2015. Recurrent reinforcement learning: a hybrid approach. arXiv:1509.03044 (2015)."},{"key":"e_1_3_2_1_22_1","volume-title":"Constructing Just-in-Time Adaptive Interventions. Phd Section Proposal","author":"Liao Peng","year":"2015","unstructured":"Peng Liao , A. Tewari , and Susan Murphy . 2015. Constructing Just-in-Time Adaptive Interventions. Phd Section Proposal ( 2015 ), 1--49. Peng Liao, A. Tewari, and Susan Murphy. 2015. Constructing Just-in-Time Adaptive Interventions. Phd Section Proposal (2015), 1--49."},{"key":"e_1_3_2_1_23_1","volume-title":"On-line outlier detection and data cleaning. Computers & chemical engineering 28, 9","author":"Liu Hancong","year":"2004","unstructured":"Hancong Liu , Sirish Shah , and Wei Jiang . 2004. On-line outlier detection and data cleaning. Computers & chemical engineering 28, 9 ( 2004 ), 1635--1647. Hancong Liu, Sirish Shah, and Wei Jiang. 2004. On-line outlier detection and data cleaning. Computers & chemical engineering 28, 9 (2004), 1635--1647."},{"key":"e_1_3_2_1_24_1","volume-title":"Richard S. Sutton, and Katie Witkiewitz.","author":"Murphy Susan A.","year":"2016","unstructured":"Susan A. Murphy , Yanzhen Deng , Eric B. Laber , Hamid Reza Maei , Richard S. Sutton, and Katie Witkiewitz. 2016 . A Batch, Off- Policy , Actor-Critic Algorithm for Optimizing the Average Reward. CoRR abs\/1607.05047 (2016). Susan A. Murphy, Yanzhen Deng, Eric B. Laber, Hamid Reza Maei, Richard S. Sutton, and Katie Witkiewitz. 2016. A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward. CoRR abs\/1607.05047 (2016)."},{"key":"e_1_3_2_1_25_1","volume-title":"Ding","author":"Nie Feiping","year":"2010","unstructured":"Feiping Nie , Heng Huang , Xiao Cai , and Chris H . Ding . 2010 . Efficient and Robust Feature Selection via Joint ?-2,1-Norms Minimization. In NIPS. 1813--1821. Feiping Nie, Heng Huang, Xiao Cai, and Chris H. Ding. 2010. Efficient and Robust Feature Selection via Joint ?-2,1-Norms Minimization. In NIPS. 1813--1821."},{"key":"e_1_3_2_1_26_1","volume-title":"Wright","author":"Nocedal Jorge","year":"2006","unstructured":"Jorge Nocedal and Stephen J . Wright . 2006 . Numerical Optimization (2nd ed.). Springer , New York. Jorge Nocedal and Stephen J. Wright. 2006. Numerical Optimization (2nd ed.). Springer, New York."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487604"},{"key":"e_1_3_2_1_28_1","volume-title":"Median Filtering is Equivalent to Sorting. arXiv:1406.1717","author":"Suomela J","year":"2014","unstructured":"J Suomela . 2014. Median Filtering is Equivalent to Sorting. arXiv:1406.1717 ( 2014 ). J Suomela. 2014. Median Filtering is Equivalent to Sorting. arXiv:1406.1717 (2014)."},{"key":"e_1_3_2_1_29_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2012","unstructured":"Richard S. Sutton and Andrew G . Barto . 2012 . Reinforcement Learning : An Introduction (2nd ed.). MIT Press , Cambridge, MA, USA. Richard S. Sutton and Andrew G. Barto. 2012. Reinforcement Learning: An Introduction (2nd ed.). MIT Press, Cambridge, MA, USA."},{"key":"e_1_3_2_1_30_1","volume-title":"Murphy","author":"Tewari Ambuj","year":"2017","unstructured":"Ambuj Tewari and Susan A . Murphy . 2017 . From Ads to Interventions : Contextual Bandits in Mobile Health. In Mobile Health: Sensors, Analytic Methods, and Applications, Jim Rehg, Susan A. Murphy, and Santosh Kumar (Eds.). Springer . Ambuj Tewari and Susan A. Murphy. 2017. From Ads to Interventions: Contextual Bandits in Mobile Health. In Mobile Health: Sensors, Analytic Methods, and Applications, Jim Rehg, Susan A. Murphy, and Santosh Kumar (Eds.). Springer."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456508"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-110-11-916"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1037\/a0034747"},{"key":"e_1_3_2_1_34_1","volume-title":"Robust decision making and its applications in machine learning","author":"Huan Xu.","unstructured":"Huan Xu. 2009. Robust decision making and its applications in machine learning . McGill University . Huan Xu. 2009. Robust decision making and its applications in machine learning. McGill University."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_78"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3107411.3107424"},{"key":"e_1_3_2_1_37_1","unstructured":"Min Yang Linli Xu Martha White Dale Schuurmans and Yao-liang Yu. 2010. Relaxed clipping: A global training method for robust regression and classification. In Advances in neural information processing systems. 2532--2540.   Min Yang Linli Xu Martha White Dale Schuurmans and Yao-liang Yu. 2010. Relaxed clipping: A global training method for robust regression and classification. In Advances in neural information processing systems. 2532--2540."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132873"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2012.01763.x"},{"key":"e_1_3_2_1_40_1","volume-title":"Proc. Assoc. Adv. Artif. Intell. (AAAI). 3217--3224","author":"Zhu Feiyun","year":"2015","unstructured":"Feiyun Zhu , Bin Fan , Xinliang Zhu , Ying Wang , Shiming Xiang , and Chunhong Pan . 2015 . 10,000+ Times Accelerated Robust Subset Selection (ARSS) . In Proc. Assoc. Adv. Artif. Intell. (AAAI). 3217--3224 . Feiyun Zhu, Bin Fan, Xinliang Zhu, Ying Wang, Shiming Xiang, and Chunhong Pan. 2015. 10,000+ Times Accelerated Robust Subset Selection (ARSS). In Proc. Assoc. Adv. Artif. Intell. (AAAI). 3217--3224."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Medical Image Computing and Computer Assisted Intervention.","author":"Zhu Feiyun","year":"2018","unstructured":"Feiyun Zhu , Jun Guo , Zheng Xu , Peng Liao , and Junzhou Huang . 2018 . Groupdriven Reinforcement Learning for Personalized mHealth Intervention . In International Conference on Medical Image Computing and Computer Assisted Intervention. Feiyun Zhu, Jun Guo, Zheng Xu, Peng Liao, and Junzhou Huang. 2018. Groupdriven Reinforcement Learning for Personalized mHealth Intervention. In International Conference on Medical Image Computing and Computer Assisted Intervention."},{"key":"e_1_3_2_1_42_1","volume-title":"The Multidisciplinary Conference on. Reinforcement Learning and Decision Making.","author":"Zhu Feiyun","year":"2017","unstructured":"Feiyun Zhu and Peng Liao . 2017 . Effective warm start for the online actor-critic reinforcement learning based mhealth intervention . In The Multidisciplinary Conference on. Reinforcement Learning and Decision Making. Feiyun Zhu and Peng Liao. 2017. Effective warm start for the online actor-critic reinforcement learning based mhealth intervention. In The Multidisciplinary Conference on. Reinforcement Learning and Decision Making."},{"key":"e_1_3_2_1_43_1","volume-title":"Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity. CoRR abs\/1409.0685","author":"Zhu Feiyun","year":"2014","unstructured":"Feiyun Zhu , Ying Wang , Bin Fan , Gaofeng Meng , and Chunhong Pan . 2014. Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity. CoRR abs\/1409.0685 ( 2014 ). http:\/\/arxiv.org\/abs\/1409.0685 Feiyun Zhu, Ying Wang, Bin Fan, Gaofeng Meng, and Chunhong Pan. 2014. Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity. CoRR abs\/1409.0685 (2014). http:\/\/arxiv.org\/abs\/1409.0685"}],"event":{"name":"BCB '18: 9th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Washington DC USA","acronym":"BCB '18","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3233547.3233554","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3233547.3233554","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3233547.3233554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:13:12Z","timestamp":1750212792000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3233547.3233554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,15]]},"references-count":42,"alternative-id":["10.1145\/3233547.3233554","10.1145\/3233547"],"URL":"https:\/\/doi.org\/10.1145\/3233547.3233554","relation":{},"subject":[],"published":{"date-parts":[[2018,8,15]]},"assertion":[{"value":"2018-08-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}