{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:13:51Z","timestamp":1767183231657},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"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":[[2023,5,28]]},"DOI":"10.1109\/icc45041.2023.10279136","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:54:10Z","timestamp":1698083650000},"page":"472-478","source":"Crossref","is-referenced-by-count":2,"title":["Communication Load Balancing via Efficient Inverse Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Abhisek","family":"Konar","sequence":"first","affiliation":[{"name":"Samsung Electronics,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi Tian","family":"Xu","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seowoo","family":"Jang","sequence":"additional","affiliation":[{"name":"Samsung Electronics,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Liu","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Machine Learning Algorithms and Applications for Sustainable Smart Grid","year":"2018","author":"wu","key":"ref13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref12","article-title":"Metaems: A meta reinforcement learning-based control framework for building energy management system","author":"zhang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref15","article-title":"A closer look at offline rl agents","author":"fu","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500379"},{"key":"ref14","article-title":"Modellight: Model-based meta-reinforcement learning for traffic signal control","author":"huang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS54753.2022.9798257"},{"key":"ref30","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"in Proc 17th International Conf on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20618"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968063"},{"key":"ref10","article-title":"Optimizing home energy management and electric vehicle charging with reinforcement learning","author":"wu","year":"0","journal-title":"ICML 2018 Workshop on machine learning for climate change"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVCI54083.2021.9661263"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118399439"},{"journal-title":"Yahoo News global traffic","year":"2022","key":"ref1"},{"key":"ref17","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref39","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500666"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061374"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2012.6398873"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/VETECF.2010.5594565"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685782"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685358"},{"key":"ref20","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"brown","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2012.6398873"},{"journal-title":"Pearson Correlation Coefficient","year":"2022","key":"ref41"},{"key":"ref22","article-title":"Traffic scenario clustering and load balancing with distilled reinforce-ment learning policies","author":"li","year":"0","journal-title":"2022 IEEE International Conference on Communications"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500379"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2014.6966140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2016.2522080"},{"key":"ref29","first-page":"1","article-title":"Load balancing and handover optimization in multiband networks using deep reinforcement learning","author":"gupta","year":"0","journal-title":"2021 IEEE Global Communications Conference (GLOBECOM)"},{"key":"ref8","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500379"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761343"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191114"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"}],"event":{"name":"ICC 2023 - IEEE International Conference on Communications","start":{"date-parts":[[2023,5,28]]},"location":"Rome, Italy","end":{"date-parts":[[2023,6,1]]}},"container-title":["ICC 2023 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10278505\/10278554\/10279136.pdf?arnumber=10279136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:01:38Z","timestamp":1699902098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10279136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,28]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icc45041.2023.10279136","relation":{},"subject":[],"published":{"date-parts":[[2023,5,28]]}}}