{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T22:50:18Z","timestamp":1753051818871,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533817","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Reza Refaei","family":"Afshar","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology,Eindhoven,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Rhuggenaath","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,Eindhoven,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,Eindhoven,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uzay","family":"Kaymak","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,Eindhoven,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2017","author":"schulman","journal-title":"Prox-imal policy optimization algorithms","key":"ref32"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TCSS.2018.2831234"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1016\/j.cie.2019.106071"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/2648584.2648585"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/3219819.3219918"},{"year":"2020","author":"yang","journal-title":"Motiac Multi-objective actor-critics for real-time bidding","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2236","DOI":"10.1609\/aaai.v34i02.5600","article-title":"Reinforcement mechanism design: With applications to dynamic pricing in sponsored search auctions","volume":"34","author":"shen","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"year":"2018","author":"wu","journal-title":"A multi-agent reinforcement learning method for impression allocation in online display advertising","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/3269206.3272021"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.5220\/0007395502560265"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CIFEr.2019.8759106"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1016\/j.orl.2021.01.008","article-title":"Maximizing revenue for publishers using header bidding and ad exchange auctions","author":"rhuggenaath","year":"2021","journal-title":"Operations Research Letters"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.2139\/ssrn.3485410"},{"key":"ref27","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"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/3355369.3355582"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-319-25023-6"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/SMC42975.2020.9283479"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/SMC.2017.8122785"},{"year":"2013","author":"mnih","journal-title":"Playing atari with deep reinforcement learning","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1561\/1500000049"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1145\/2623330.2623357"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/SOLI.2014.6960761"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1017\/S0269888918000292"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1209\/epl\/i2000-00208-x"},{"key":"ref21","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/LRA.2019.2899918"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.18653\/v1\/W15-4655"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/SMC.2017.8122643"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1145\/3292500.3330729"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533817.pdf?arnumber=9533817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:32:20Z","timestamp":1659483140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533817","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}