{"id":"https://openalex.org/W3145052169","doi":"https://doi.org/10.1109/jsac.2021.3087248","title":"Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels","display_name":"Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3145052169","doi":"https://doi.org/10.1109/jsac.2021.3087248","mag":"3145052169"},"language":"en","primary_location":{"id":"doi:10.1109/jsac.2021.3087248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2021.3087248","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Communications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.10369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064236204","display_name":"Tze-Yang Tung","orcid":"https://orcid.org/0000-0003-2716-5211"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tze-Yang Tung","raw_affiliation_strings":["Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0003-2716-5211","affiliations":[{"raw_affiliation_string":"Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035697090","display_name":"Szymon Kobus","orcid":"https://orcid.org/0009-0006-3605-9073"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Szymon Kobus","raw_affiliation_strings":["Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joan Pujol Roig","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joan Pujol Roig","raw_affiliation_strings":["Samsung Electronics Research and Development Institute UK, Staines-upon-Thames, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Research and Development Institute UK, Staines-upon-Thames, U.K","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016883501","display_name":"Den\u0131z G\u00fcnd\u00fcz","orcid":"https://orcid.org/0000-0002-7725-395X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Deniz Gunduz","raw_affiliation_strings":["Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6513,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74849162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"39","issue":"8","first_page":"2590","last_page":"2603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9711999893188477,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8828649520874023},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8712828159332275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7744494676589966},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6181249022483826},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.583669900894165},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5748316049575806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46222010254859924},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4499073624610901},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44779136776924133},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.4360286295413971},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32811135053634644},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3151828646659851},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.22597697377204895},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.20730561017990112},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13810598850250244}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8828649520874023},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8712828159332275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744494676589966},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6181249022483826},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.583669900894165},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5748316049575806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46222010254859924},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4499073624610901},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44779136776924133},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.4360286295413971},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32811135053634644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3151828646659851},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.22597697377204895},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.20730561017990112},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13810598850250244},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/jsac.2021.3087248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2021.3087248","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Communications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2101.10369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.10369","pdf_url":"https://arxiv.org/pdf/2101.10369","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3145052169","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.10369.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.10369","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.10369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.10369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.10369","pdf_url":"https://arxiv.org/pdf/2101.10369","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4399999976158142,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6072283711","display_name":null,"funder_award_id":"677854","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7846425480","display_name":null,"funder_award_id":"677854","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G8105621258","display_name":"Communication-Aware Dynamic Edge Computing (CONNECT)","funder_award_id":"EP/T023600/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G98698327","display_name":null,"funder_award_id":"EP/T023600/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W2017957151","https://openalex.org/W2050509222","https://openalex.org/W2064675550","https://openalex.org/W2080213916","https://openalex.org/W2081525555","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2150671164","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2621379712","https://openalex.org/W2666368276","https://openalex.org/W2756196406","https://openalex.org/W2798948906","https://openalex.org/W2893836673","https://openalex.org/W2898338514","https://openalex.org/W2902806690","https://openalex.org/W2906647810","https://openalex.org/W2914351253","https://openalex.org/W2946889564","https://openalex.org/W2950472486","https://openalex.org/W2954559956","https://openalex.org/W2963000099","https://openalex.org/W2963588154","https://openalex.org/W2963717208","https://openalex.org/W2963937357","https://openalex.org/W2964121744","https://openalex.org/W2964198392","https://openalex.org/W2968026845","https://openalex.org/W2983400533","https://openalex.org/W2990330051","https://openalex.org/W2993383518","https://openalex.org/W3016715915","https://openalex.org/W3021482604","https://openalex.org/W3024893463","https://openalex.org/W3034611340","https://openalex.org/W3036851434","https://openalex.org/W3044517463","https://openalex.org/W3102125291","https://openalex.org/W3120141412","https://openalex.org/W3123911006","https://openalex.org/W3134818623","https://openalex.org/W3189491540","https://openalex.org/W6631190155","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6731193076","https://openalex.org/W6738795958","https://openalex.org/W6738796088","https://openalex.org/W6743367460","https://openalex.org/W6744537943","https://openalex.org/W6751139674","https://openalex.org/W6755542948","https://openalex.org/W6758763022","https://openalex.org/W6762869072","https://openalex.org/W6764943343","https://openalex.org/W6779940784","https://openalex.org/W6781197983","https://openalex.org/W6786345871","https://openalex.org/W6787450248","https://openalex.org/W6789876269","https://openalex.org/W6815241486"],"related_works":["https://openalex.org/W3122208696","https://openalex.org/W2895183999","https://openalex.org/W3037124050","https://openalex.org/W2903731519","https://openalex.org/W2916210063","https://openalex.org/W3034977961","https://openalex.org/W1504806788","https://openalex.org/W2395575420","https://openalex.org/W3047315308","https://openalex.org/W2990330051","https://openalex.org/W1580086873","https://openalex.org/W2963677857","https://openalex.org/W2933085415","https://openalex.org/W3098297242","https://openalex.org/W2006303459","https://openalex.org/W2982169171","https://openalex.org/W3201099806","https://openalex.org/W2184461682","https://openalex.org/W3132645056","https://openalex.org/W2911389451"],"abstract_inverted_index":{"We":[0,183],"propose":[1],"a":[2,32,44,53,79,115,133,151,155,212],"novel":[3],"formulation":[4],"of":[5,24,92,95,106,236,243],"the":[6,63,70,93,96,99,107,110,117,140,145,159,170,174,188,193,201,207,233,241],"\u201ceffectiveness":[7],"problem\u201d":[8],"in":[9,17,35,43,61,65,169],"communications,":[10],"put":[11],"forth":[12],"by":[13,26],"Shannon":[14],"and":[15,41,98,158,230],"Weaver":[16],"their":[18],"seminal":[19],"work":[20],"\u201cThe":[21],"Mathematical":[22],"Theory":[23],"Communication\u201d,":[25],"considering":[27],"multiple":[28],"agents":[29,118],"communicating":[30],"over":[31,78,132,154],"noisy":[33,80,84,134,156],"channel":[34,86],"order":[36],"to":[37,67,122,129,149,161,180,198,226],"achieve":[38],"better":[39],"coordination":[40],"cooperation":[42],"multi-agent":[45,54],"reinforcement":[46,238],"learning":[47,239],"(MARL)":[48],"framework.":[49],"Specifically,":[50],"we":[51],"consider":[52],"partially":[55],"observable":[56],"Markov":[57],"decision":[58],"process":[59],"(MA-POMDP),":[60],"which":[62,216],"agents,":[64],"addition":[66],"interacting":[68],"with":[69,75,124],"environment,":[71,97],"can":[72,112],"also":[73,128],"communicate":[74,130],"each":[76,101,125],"other":[77,126],"communication":[81,85,142,176,202,245],"channel.":[82,135],"The":[83],"is":[87,104,148,196,203,211],"considered":[88,204],"explicitly":[89],"as":[90],"part":[91,105],"dynamics":[94],"message":[100,152],"agent":[102,111],"sends":[103],"action":[108],"that":[109,164,187,199],"take.":[113],"As":[114],"result,":[116],"learn":[119],"not":[120],"only":[121],"collaborate":[123],"but":[127],"\u201ceffectively\u201d":[131],"This":[136,210],"framework":[137,163,195],"generalizes":[138],"both":[139],"traditional":[141],"problem,":[143],"where":[144,173,200],"main":[146],"goal":[147],"convey":[150],"reliably":[153],"channel,":[157],"\u201clearning":[160],"communicate\u201d":[162],"has":[165,217],"received":[166],"recent":[167],"attention":[168],"MARL":[171],"literature,":[172],"underlying":[175,208],"channels":[177],"are":[178],"assumed":[179],"be":[181],"error-free.":[182],"show":[184],"via":[185],"examples":[186],"joint":[189],"policy":[190],"learned":[191],"using":[192],"proposed":[194],"superior":[197],"separately":[205],"from":[206,222],"MA-POMDP.":[209],"very":[213],"powerful":[214],"framework,":[215],"many":[218],"real":[219],"world":[220],"applications,":[221],"autonomous":[223],"vehicle":[224],"planning":[225],"drone":[227],"swarm":[228],"control,":[229],"opens":[231],"up":[232],"rich":[234],"toolbox":[235],"deep":[237],"for":[240],"design":[242],"multi-user":[244],"systems.":[246]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}