{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:21:58Z","timestamp":1730254918498,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412373","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"4865-4872","source":"Crossref","is-referenced-by-count":0,"title":["Can Reinforcement Learning Lead to Healthy Life?: Simulation Study Based on User Activity Logs"],"prefix":"10.1109","author":[{"given":"Masami","family":"Takahashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Kohjima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeshi","family":"Kurashima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroyuki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref12","first-page":"279","volume":"8","author":"jch","year":"1992","journal-title":"Q-learning Machine Learning"},{"key":"ref13","first-page":"229","author":"williams","year":"1992","journal-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning Machine learning 8 3–4"},{"key":"ref14","article-title":"Continuous state-space models for optimal sepsis treatment-a deep reinforcement learning approach","author":"raghu","year":"2017","journal-title":"arXiv preprint arXiv 1705 08422"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5229-0"},{"journal-title":"Encouraging Physical Activity in Patients With Diabetes Intervention Using a Reinforcement Learning System J Med Internet Res","year":"2017","author":"yom-tov","key":"ref16"},{"key":"ref17","article-title":"Narrowing Reinforcement Learning: Overcoming the Cold Start Problem for Personalized Health Interventions","author":"seyed","year":"0","journal-title":"PRIMA 2018 Principles and Practice of Multi-Agent Systems Proceedings"},{"journal-title":"Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"martin","key":"ref18"},{"key":"ref19","first-page":"1196","author":"natarajan","year":"2013","journal-title":"Learning with noisy labels In Advances in neural information processing systems"},{"key":"ref4","first-page":"354","volume":"7676","author":"david","year":"2017","journal-title":"Mastering the game of go without human knowledge Nature 550"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3341162.3343809"},{"journal-title":"Investigating the effectiveness of cohort-based sleep recommendations Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","year":"0","author":"daskalova","key":"ref5"},{"key":"ref8","first-page":"1265","volume":"6","author":"shani","year":"2005","journal-title":"An MDP-based recommender system Journal of Machine Learning Research"},{"journal-title":"Human-level control through deep reinforcement learning Nature 518","year":"2015","author":"mnih","key":"ref7"},{"journal-title":"Nursing for the people with lifestyle-related diseases in Japan","year":"0","key":"ref2"},{"journal-title":"Global recommendations on physical activity for health Geneva Switzerland WHO","year":"2010","key":"ref1"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref22","first-page":"961","author":"heilbron","year":"0","journal-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref21","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545435"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412373.pdf?arnumber=9412373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:55Z","timestamp":1652197255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412373","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}