{"id":"https://openalex.org/W4294956331","doi":"https://doi.org/10.48550/arxiv.2209.01288","title":"Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning","display_name":"Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-09-02","ids":{"openalex":"https://openalex.org/W4294956331","doi":"https://doi.org/10.48550/arxiv.2209.01288"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.01288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.01288","pdf_url":"https://arxiv.org/pdf/2209.01288","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.01288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089728351","display_name":"Diyi Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Diyi","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458165","display_name":"Chi Zhang","orcid":"https://orcid.org/0009-0003-3243-0558","observed_orcids":["https://orcid.org/0009-0003-3243-0558","https://orcid.org/0000-0001-7374-1940"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589","observed_orcids":["https://orcid.org/0000-0002-1609-8589","https://orcid.org/0009-0001-8676-5308"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasanna, Viktor","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089756690","display_name":"Bhaskar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnamachari, Bhaskar","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9945999979972839,"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":0.9945999979972839,"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/T11031","display_name":"Game Theory and Applications","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.0007999999797903001,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8920000195503235},{"id":"https://openalex.org/keywords/cooperative-multi-agent-systems","display_name":"cooperative multi-agent systems","score":0.6129999756813049},{"id":"https://openalex.org/keywords/communication-strategies","display_name":"communication strategies","score":0.7480000257492065},{"id":"https://openalex.org/keywords/wireless-networks","display_name":"wireless networks","score":0.8799999952316284},{"id":"https://openalex.org/keywords/communication-timing","display_name":"communication timing","score":0.5870000123977661},{"id":"https://openalex.org/keywords/network-conditions","display_name":"network conditions","score":0.4180000126361847},{"id":"https://openalex.org/keywords/agent-mobility","display_name":"agent mobility","score":0.5429999828338623},{"id":"https://openalex.org/keywords/communication-efficiency","display_name":"communication efficiency","score":0.6179999709129333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.799787163734436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884925603866577},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5795828104019165},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5249966382980347},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5030013918876648},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.4896695911884308},{"id":"https://openalex.org/C83529365","wikidata":"https://www.wikidata.org/wiki/Q4972103","display_name":"Broadcast communication network","level":2,"score":0.4879271686077118},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.46372315287590027},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.456932008266449},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.4533393681049347},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4472113251686096},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44585657119750977},{"id":"https://openalex.org/C2983568541","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Information transmission","level":2,"score":0.4345208406448364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3237965404987335},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19361940026283264},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.01288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.01288","pdf_url":"https://arxiv.org/pdf/2209.01288","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,"listed_in":[],"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":"doi:10.48550/arxiv.2209.01288","doi":"https://doi.org/10.48550/arxiv.2209.01288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.01288","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.01288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.01288","pdf_url":"https://arxiv.org/pdf/2209.01288","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294956331.pdf","grobid_xml":"https://content.openalex.org/works/W4294956331.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2010744519","https://openalex.org/W2119717200","https://openalex.org/W2137983211","https://openalex.org/W2756196406","https://openalex.org/W2951218345","https://openalex.org/W3096656822"],"related_works":["https://openalex.org/W7124248725","https://openalex.org/W4392158183","https://openalex.org/W3035448954","https://openalex.org/W2990927597","https://openalex.org/W7212364548","https://openalex.org/W4396523522","https://openalex.org/W4401462044","https://openalex.org/W4385637469","https://openalex.org/W4315630270","https://openalex.org/W2988210831"],"abstract_inverted_index":{"In":[0],"Multi-Agent":[1],"Reinforcement":[2],"Learning,":[3],"communication":[4,42,56,84,128],"is":[5],"critical":[6],"to":[7,22,39,78,95],"encourage":[8],"cooperation":[9],"among":[10],"agents.":[11],"Communication":[12],"in":[13,31,122],"realistic":[14,114],"wireless":[15,65,75,115],"networks":[16],"can":[17],"be":[18],"highly":[19],"unreliable":[20],"due":[21],"network":[23,76,116],"conditions":[24],"varying":[25],"with":[26,74,131],"agents'":[27],"mobility,":[28],"and":[29,83,106,127],"stochasticity":[30],"the":[32,53,81,104],"transmission":[33],"process.":[34],"We":[35],"propose":[36],"a":[37,90],"framework":[38],"learn":[40,52],"practical":[41],"strategies":[43],"by":[44],"addressing":[45],"three":[46],"fundamental":[47],"questions:":[48],"(1)":[49],"When:":[50],"Agents":[51,70,88],"timing":[54],"of":[55,103,108],"based":[57],"on":[58],"not":[59],"only":[60],"message":[61,72,93],"importance":[62],"but":[63],"also":[64],"channel":[66],"conditions.":[67],"(2)":[68],"What:":[69],"augment":[71],"contents":[73],"measurements":[77],"better":[79],"select":[80],"game":[82,123],"actions.":[85],"(3)":[86],"How:":[87],"use":[89],"novel":[91],"neural":[92],"encoder":[94],"preserve":[96],"all":[97],"information":[98],"from":[99],"received":[100],"messages,":[101],"regardless":[102],"number":[105],"order":[107],"messages.":[109],"Simulating":[110],"standard":[111],"benchmarks":[112],"under":[113],"settings,":[117],"we":[118],"show":[119],"significant":[120],"improvements":[121],"performance,":[124],"convergence":[125],"speed":[126],"efficiency":[129],"compared":[130],"state-of-the-art.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-09-08T00:00:00"}