{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:22:07Z","timestamp":1774718527505,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"name":"E! 11582"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tai.2022.3186292","type":"journal-article","created":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T16:49:11Z","timestamp":1656348551000},"page":"428-437","source":"Crossref","is-referenced-by-count":12,"title":["An Automated Deep Reinforcement Learning Pipeline for Dynamic Pricing"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1558-8380","authenticated-orcid":false,"given":"Reza Refaei","family":"Afshar","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"given":"Jason","family":"Rhuggenaath","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5073-0787","authenticated-orcid":false,"given":"Yingqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4500-9098","authenticated-orcid":false,"given":"Uzay","family":"Kaymak","sequence":"additional","affiliation":[{"name":"Jheronimus Academy of Data Science, ‘s-Hertogenbosch, Netherlands"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9283479"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330729"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5600"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.32"},{"key":"ref31","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","author":"chou","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100970"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6171"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2021.01.008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124760"},{"key":"ref2","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sorms.2015.03.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5220\/0007395502560265"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272021"},{"key":"ref19","first-page":"2702","article-title":"Discriminative embeddings of latent variable models for structured data","author":"dai","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","article-title":"Automated reinforcement learning: An overview","author":"afshar","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794206"},{"key":"ref23","first-page":"1352","article-title":"Distributional policy optimization: An alternative approach for continuous control","author":"tessler","year":"0","journal-title":"Proc Int Conf Inf Process Syst"},{"key":"ref26","first-page":"18","article-title":"Reinforcement learning algorithm selection","author":"laroche","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref20","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"0","journal-title":"Proc Int Conf Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"ref21","first-page":"81","article-title":"A state aggregation approach for solving knapsack problem with deep reinforcement learning","author":"afshar","year":"0","journal-title":"Proc Asian Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v32i1.19829"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CLEI.2017.8226439"},{"key":"ref29","article-title":"Sample-efficient automated deep reinforcement learning","author":"franke","year":"2020","journal-title":"Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1108\/IJCHM-09-2016-0540"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/app7111160"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2019.8759123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.11.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533817"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2020.3680"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0725"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10132888\/09807363.pdf?arnumber=9807363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:37Z","timestamp":1755911317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9807363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":32,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3186292","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}