{"id":"https://openalex.org/W4385750282","doi":"https://doi.org/10.1007/s00521-025-11782-6","title":"An in-depth analysis of discretization methods for communication learning using backpropagation with multi-agent reinforcement learning","display_name":"An in-depth analysis of discretization methods for communication learning using backpropagation with multi-agent reinforcement learning","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W4385750282","doi":"https://doi.org/10.1007/s00521-025-11782-6"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11782-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11782-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11782-6.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11782-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041138120","display_name":"Astrid Vanneste","orcid":"https://orcid.org/0000-0002-6742-6722"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Astrid Vanneste","raw_affiliation_strings":["IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-6742-6722","affiliations":[{"raw_affiliation_string":"IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074520540","display_name":"Simon Vanneste","orcid":"https://orcid.org/0000-0002-9664-9925"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Simon Vanneste","raw_affiliation_strings":["IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006262997","display_name":"Tom De Schepper","orcid":"https://orcid.org/0000-0002-2969-3133"},"institutions":[{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tom De Schepper","raw_affiliation_strings":["AI & Data Department, IMEC, 3001, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI & Data Department, IMEC, 3001, Leuven, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015248763","display_name":"Siegfried Mercelis","orcid":"https://orcid.org/0000-0001-9355-6566"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Siegfried Mercelis","raw_affiliation_strings":["IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008171683","display_name":"Peter Hellinckx","orcid":"https://orcid.org/0000-0001-8029-4720"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Peter Hellinckx","raw_affiliation_strings":["M4S - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp, Groenenborgerlaan 171, 2020, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M4S - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp, Groenenborgerlaan 171, 2020, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084961388","display_name":"Kevin Mets","orcid":"https://orcid.org/0000-0002-4812-4841"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kevin Mets","raw_affiliation_strings":["IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - IMEC, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074520540"],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00146237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"38","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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":0.9940999746322632,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9848999977111816,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9711999893188477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7927838563919067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561123371124268},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6842151880264282},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6051976084709167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4872109293937683},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4511503577232361},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35226577520370483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09771865606307983},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09636646509170532}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7927838563919067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561123371124268},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6842151880264282},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6051976084709167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4872109293937683},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4511503577232361},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35226577520370483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09771865606307983},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09636646509170532},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s00521-025-11782-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11782-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11782-6.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2308.04938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.04938","pdf_url":"https://arxiv.org/pdf/2308.04938","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.04938","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.04938","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11782-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11782-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11782-6.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3038896941","display_name":"Learning to communicate efficiently with multi-agent reinforcement learning for distributed control applications","funder_award_id":"1S12121N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G5247268040","display_name":"Multi-Agent Communication and Behaviour Training using Reinforcement Learning","funder_award_id":"1S94120N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385750282.pdf","grobid_xml":"https://content.openalex.org/works/W4385750282.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2799209613","https://openalex.org/W2793786119","https://openalex.org/W1507702947"],"abstract_inverted_index":{"Communication":[0],"is":[1,30,52,233],"crucial":[2],"in":[3,89,121,174,201,227],"multi-agent":[4],"reinforcement":[5],"learning":[6,92,126,145,154],"when":[7,54],"agents":[8,29,44,131],"are":[9,87],"not":[10,239],"able":[11],"to":[12,24,41,57,61,79,99,163,176,185,223],"observe":[13],"the":[14,18,31,63,122,165,171,178,196,205,214,219,224,230,234,244],"full":[15],"state":[16],"of":[17,33,48,124,209,229,243],"environment.":[19],"The":[20],"most":[21],"common":[22],"approach":[23,146],"allow":[25],"learned":[26],"communication":[27,36,73,91,125,144,179],"between":[28,43],"use":[32,58],"a":[34,46,71,114,143],"differentiable":[35],"channel":[37],"that":[38,195,237],"allows":[39,183],"gradients":[40,67,128],"flow":[42,69],"as":[45,111,113],"form":[47],"feedback.":[49],"However,":[50,84],"this":[51,82,103,119,202],"challenging":[53],"we":[55,105,140],"want":[56],"discrete":[59,72],"messages":[60],"reduce":[62],"message":[64],"size,":[65],"since":[66],"cannot":[68],"through":[70],"channel.":[74],"Previous":[75],"work":[76],"proposed":[77,200],"methods":[78,86,110,212],"deal":[80],"with":[81,153],"problem.":[83],"these":[85],"tested":[88,245],"different":[90,215],"architectures":[93],"and":[94,132,150,157,232],"environments,":[95],"making":[96],"it":[97,169],"hard":[98],"compare":[100,106],"them.":[101],"In":[102,138],"paper,":[104,203],"several":[107,136],"state-of-the-art":[108],"discretization":[109,211],"well":[112],"novel":[115,197],"approach.":[116],"We":[117],"do":[118],"comparison":[120],"context":[123],"using":[127],"from":[129],"other":[130],"perform":[133,186],"tests":[134],"on":[135,148,188,241],"environments.":[137,191,216,246],"addition,":[139],"present":[141],"COMA-DIAL,":[142],"based":[147],"DIAL":[149,175],"COMA":[151,162],"extended":[152],"rate":[155],"scaling":[156],"adapted":[158],"exploration.":[159],"COMA-DIAL":[160,182],"uses":[161,170],"learn":[164,177],"action":[166],"policy":[167],"while":[168],"mechanism":[172],"introduced":[173],"policy.":[180],"Using":[181],"us":[184],"experiments":[187,231],"more":[189],"complex":[190],"Our":[192],"results":[193,207],"show":[194],"ST-DRU":[198],"method,":[199],"achieves":[204,218],"best":[206,220,225],"out":[208],"all":[210],"across":[213],"It":[217],"or":[221],"close":[222],"performance":[226],"each":[228],"only":[235],"method":[236],"does":[238],"fail":[240],"any":[242]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2023-08-11T00:00:00"}
