{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:10:55Z","timestamp":1780535455071,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/www.ieee.org\/publications_standards\/publications\/rights\/ieeecopyrightform.pdf"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.ieee.org\/publications_standards\/publications\/rights\/ieeecopyrightform.pdf"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. NSF","doi-asserted-by":"publisher","award":["ECCS-1711056"],"award-info":[{"award-number":["ECCS-1711056"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Combat Capabilities Development Command of the U.S. Army Research Laboratory through Cooperative Agreement","doi-asserted-by":"publisher","award":["W911NF-17-2-0183"],"award-info":[{"award-number":["W911NF-17-2-0183"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/jsait.2021.3073834","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T20:31:26Z","timestamp":1618605086000},"page":"627-640","source":"Crossref","is-referenced-by-count":18,"title":["Belief Propagation Decoding of Short Graph-Based Channel Codes via Reinforcement Learning"],"prefix":"10.1109","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0699-5312","authenticated-orcid":false,"given":"Salman","family":"Habib","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1759-5026","authenticated-orcid":false,"given":"Allison","family":"Beemer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0942-8006","authenticated-orcid":false,"given":"Jorg","family":"Kliewer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.838370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/18.910580"},{"key":"ref31","first-page":"437","article-title":"Multi-armed bandit algorithms and empirical evaluation","author":"vermorel","year":"2005","journal-title":"Proc Eur Conf Mach Learn (ECML)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/2200000070"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3626-0"},{"key":"ref35","author":"mackay","year":"2003","journal-title":"Information Theory Inference and Learning Algorithms"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2015.7282488"},{"key":"ref10","author":"sutton","year":"2015","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2788405"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2955724"},{"key":"ref13","first-page":"2758","article-title":"Deep learning based channel codes for point-to-point communication channels","author":"jiang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"2329","article-title":"Hyper-graph-network decoders for block codes","author":"nachmani","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","author":"doan","year":"2020","journal-title":"Decoding polar codes with reinforcement learning"},{"key":"ref16","author":"liao","year":"2020","journal-title":"Construction of polar codes with reinforcement learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919799"},{"key":"ref18","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262802"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6852099"},{"key":"ref27","first-page":"543","article-title":"Array codes as low-density parity-check codes","author":"fan","year":"2000","journal-title":"Proc Int Symp Turbo Codes Rel Topics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1962.1057683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/18.959255"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1979.tb01068.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/4234.905935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/26.768759"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1981.1056404"},{"key":"ref2","article-title":"Learning to decode: Reinforcement learning for decoding of sparse graph-based channel codes","author":"habib","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2010.101910.070303"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174337"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50034-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015355"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102454"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650243"},{"key":"ref23","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1998","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2034781"},{"key":"ref25","first-page":"3111","article-title":"Q-learning with nearest neighbors","author":"shah","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/9459757\/9406115-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/9459757\/09406115.pdf?arnumber=9406115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T22:36:51Z","timestamp":1636411011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9406115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":36,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2021.3073834","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}