{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:18:40Z","timestamp":1774678720842,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003699","name":"Research and Development Program of the Korea Railroad Research Institute, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003699","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Bio-Mimetic Robot Research Center"},{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration, Agency for Defense Development","doi-asserted-by":"publisher","award":["UD190018ID"],"award-info":[{"award-number":["UD190018ID"]}],"id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF), Ministry of Science and ICT, through the Basic Science Research Programs","doi-asserted-by":"publisher","award":["NRF-2019R1C1C1006806"],"award-info":[{"award-number":["NRF-2019R1C1C1006806"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF), Ministry of Science and ICT, through the Basic Science Research Programs","doi-asserted-by":"publisher","award":["NRF-2020R1G1A1003759"],"award-info":[{"award-number":["NRF-2020R1G1A1003759"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3026362","type":"journal-article","created":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T20:30:09Z","timestamp":1600979409000},"page":"179678-179691","source":"Crossref","is-referenced-by-count":3,"title":["On the Design of Tailored Neural Networks for Energy Harvesting Broadcast Channels: A Reinforcement Learning Approach"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3860-8962","authenticated-orcid":false,"given":"Heasung","family":"Kim","sequence":"first","affiliation":[]},{"given":"Jungtai","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6513-1237","authenticated-orcid":false,"given":"Wonjae","family":"Shin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2802-2143","authenticated-orcid":false,"given":"Heecheol","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Nayoung","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7794-5593","authenticated-orcid":false,"given":"Seong Jin","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6804-980X","authenticated-orcid":false,"given":"Jungwoo","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2919","article-title":"Fast and flexible monotonic functions with ensembles of lattices","author":"fard","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"3790","article-title":"Monotonic calibrated interpolated look-up tables","volume":"17","author":"gupta","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1021\/ci0342472"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266507"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref37","first-page":"661","article-title":"Monotonic networks","author":"sill","year":"1998","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"arXiv 1512 07679"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139030687"},{"key":"ref34","article-title":"Regularization for deep learning: A taxonomy","author":"kuka?ka","year":"2017","journal-title":"ArXiv 1710 10686"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.030413.121120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2295603"},{"key":"ref40","first-page":"6834","article-title":"Diminishing returns shape constraints for interpretability and regularization","author":"gupta","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511405"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647681"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2611858"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462056"},{"key":"ref16","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref19","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programmin"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1109\/JSAC.2014.141212","article-title":"Throughput optimal policies for energy harvesting wireless transmitters with non-ideal circuit power","volume":"32","author":"xu","year":"2014","journal-title":"IEEE J Sel Areas Commun"},{"key":"ref28","first-page":"1","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.012412.110805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2011.120911.101813"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.032812.110813"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2548459"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2387380"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2011.112811.100349"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110921"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013583"},{"key":"ref20","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref22","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref24","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/20062066"},{"key":"ref23","first-page":"968","article-title":"Gradient descent for general reinforcement learning","author":"baird","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref26","article-title":"Efficient parallel methods for deep reinforcement learning","author":"clemente","year":"2017","journal-title":"arXiv 1705 04862"},{"key":"ref25","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09205303.pdf?arnumber=9205303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:09Z","timestamp":1639770969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9205303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3026362","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}