{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,7]],"date-time":"2025-12-07T13:08:22Z","timestamp":1765112902120},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.23919\/fruct48121.2019.8981496","type":"proceedings-article","created":{"date-parts":[[2020,2,7]],"date-time":"2020-02-07T03:50:27Z","timestamp":1581047427000},"page":"373-382","source":"Crossref","is-referenced-by-count":2,"title":["Real-Time Bidding with Soft Actor-Critic Reinforcement Learning in Display Advertising"],"prefix":"10.23919","author":[{"given":"Daria","family":"Yakovleva","sequence":"first","affiliation":[]},{"given":"Artem","family":"Popov","sequence":"additional","affiliation":[]},{"given":"Andrey","family":"Filchenkov","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"article-title":"A multi-agent reinforcement learning method for impression allocation in online display advertising","year":"2018","author":"wu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272021"},{"article-title":"A new optimization layer for real-time bidding advertising campaigns","year":"2018","author":"micchi","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2775228"},{"key":"ref16","first-page":"425","article-title":"Optimization of a ssp’s header bidding strategy using thompson sampling","author":"jauvion","year":"2018","journal-title":"ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"ref17","first-page":"2249","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648590"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"journal-title":"Regulation user migration amazon is the duopolys future assured?","year":"2019","author":"mcdonald","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICMSE.2014.6930205"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/1500000049"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623633"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339655"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2018.1098"},{"article-title":"Forecasting granular audience size for online advertising","year":"2019","author":"sinha","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69179-4_50"}],"event":{"name":"2019 25th Conference of Open Innovations Association (FRUCT)","start":{"date-parts":[[2019,11,5]]},"location":"Helsinki, Finland","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 25th Conference of Open Innovations Association (FRUCT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8967174\/8981488\/08981496.pdf?arnumber=8981496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,7]],"date-time":"2020-05-07T22:11:46Z","timestamp":1588889506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8981496\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/fruct48121.2019.8981496","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}