{"id":"https://openalex.org/W4387872667","doi":"https://doi.org/10.1109/icc45041.2023.10278640","title":"Low Entropy Communication in Multi-Agent Reinforcement Learning","display_name":"Low Entropy Communication in Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-28","ids":{"openalex":"https://openalex.org/W4387872667","doi":"https://doi.org/10.1109/icc45041.2023.10278640"},"language":"en","primary_location":{"id":"doi:10.1109/icc45041.2023.10278640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icc45041.2023.10278640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2023 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050690756","display_name":"Lebin Yu","orcid":"https://orcid.org/0000-0003-4566-3820"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lebin Yu","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089892883","display_name":"Yunbo Qiu","orcid":"https://orcid.org/0000-0001-5069-6673"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Qiu","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090362440","display_name":"Qiexiang Wang","orcid":"https://orcid.org/0000-0002-8037-8227"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiexiang Wang","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441855","display_name":"Xudong Zhang","orcid":"https://orcid.org/0000-0002-6465-7437"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Zhang","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370361","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0001-7683-6937"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050690756"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66205705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"5173","last_page":"5178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9919999837875366,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574164271354675},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7078955769538879},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6793738007545471},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.45324766635894775},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.369911253452301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36090338230133057},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19755271077156067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574164271354675},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7078955769538879},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6793738007545471},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.45324766635894775},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.369911253452301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36090338230133057},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19755271077156067},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc45041.2023.10278640","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icc45041.2023.10278640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2023 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W285471286","https://openalex.org/W1542941925","https://openalex.org/W1686946872","https://openalex.org/W1995875735","https://openalex.org/W2119717200","https://openalex.org/W2122538988","https://openalex.org/W2395575420","https://openalex.org/W2914316962","https://openalex.org/W2962764167","https://openalex.org/W2964338167","https://openalex.org/W2988490775","https://openalex.org/W2994864869","https://openalex.org/W2995815314","https://openalex.org/W3083668477","https://openalex.org/W3090254537","https://openalex.org/W3096358451","https://openalex.org/W3127063420","https://openalex.org/W3128366769","https://openalex.org/W3129246708","https://openalex.org/W3132069826","https://openalex.org/W3201099806","https://openalex.org/W3210169707","https://openalex.org/W3213030159","https://openalex.org/W4287119204","https://openalex.org/W4288601262","https://openalex.org/W4289100326","https://openalex.org/W4289363497","https://openalex.org/W4315630270","https://openalex.org/W6637108112","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6755542948","https://openalex.org/W6757781149","https://openalex.org/W6757784512","https://openalex.org/W6769091550","https://openalex.org/W6770332567","https://openalex.org/W6771514159","https://openalex.org/W6774209130","https://openalex.org/W6782512527","https://openalex.org/W6783960556","https://openalex.org/W6784951334","https://openalex.org/W6790614080","https://openalex.org/W6796534486","https://openalex.org/W6801742125","https://openalex.org/W6803253082","https://openalex.org/W6803621620"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Communication":[0],"in":[1,14,32,45,58],"multi-agent":[2,17,59],"reinforcement":[3],"learning":[4],"has":[5],"been":[6],"drawing":[7],"attention":[8],"recently":[9],"for":[10],"its":[11],"significant":[12],"role":[13],"cooperation.":[15],"However,":[16],"systems":[18],"may":[19],"suffer":[20],"from":[21],"limitations":[22],"on":[23,101],"communication":[24,30,104],"resources":[25],"and":[26,110],"thus":[27],"need":[28],"efficient":[29],"techniques":[31],"real-world":[33],"scenarios.":[34],"According":[35],"to":[36,41,54,121],"the":[37,66,93],"Shannon-Hartley":[38],"theorem,":[39],"messages":[40,96],"be":[42],"transmitted":[43],"reliably":[44],"worse":[46],"channels":[47],"require":[48],"lower":[49],"entropy.":[50],"Therefore,":[51],"we":[52,81],"aim":[53],"reduce":[55,116],"message":[56,117],"entropy":[57,69,90,118],"communication.":[60],"A":[61],"fundamental":[62],"challenge":[63],"is":[64],"that":[65,112],"gradients":[67],"of":[68,95,127],"are":[70],"either":[71],"0":[72],"or":[73],"\u221e,":[74],"disabling":[75],"gradient-based":[76],"methods.":[77],"To":[78],"handle":[79],"it,":[80],"propose":[82],"a":[83],"pseudo":[84],"gradient":[85],"descent":[86],"scheme,":[87],"which":[88],"reduces":[89],"by":[91,119],"adjusting":[92],"distributions":[94],"wisely.":[97],"We":[98],"conduct":[99],"experiments":[100],"two":[102],"base":[103],"frameworks":[105],"with":[106,123],"six":[107],"environment":[108],"settings":[109],"find":[111],"our":[113],"scheme":[114],"can":[115],"up":[120],"90%":[122],"nearly":[124],"no":[125],"loss":[126],"cooperation":[128],"performance.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}