{"id":"https://openalex.org/W3005657850","doi":"https://doi.org/10.1109/lra.2020.2972862","title":"Simultaneous Policy and Discrete Communication Learning for Multi-Agent Cooperation","display_name":"Simultaneous Policy and Discrete Communication Learning for Multi-Agent Cooperation","publication_year":2020,"publication_date":"2020-02-11","ids":{"openalex":"https://openalex.org/W3005657850","doi":"https://doi.org/10.1109/lra.2020.2972862","mag":"3005657850"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2972862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2972862","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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/A5081604594","display_name":"Benjamin Freed","orcid":"https://orcid.org/0000-0003-3741-3709"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benjamin Freed","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-3741-3709","affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069667034","display_name":"Guillaume Sartoretti","orcid":"https://orcid.org/0000-0002-7579-9916"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guillaume Sartoretti","raw_affiliation_strings":["Department of Mechanical Engineering at the National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7579-9916","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering at the National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048906141","display_name":"Howie Choset","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howie Choset","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-5434-7945","affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081604594"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8154,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78353645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"2","first_page":"2498","last_page":"2505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/leverage","display_name":"Leverage (statistics)","score":0.7824851274490356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7272371053695679},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6985481977462769},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6787448525428772},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5326604247093201},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5299690365791321},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5055649280548096},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4449479579925537},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.43618154525756836},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43099427223205566},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4122703969478607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3573368787765503},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13678476214408875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10596504807472229},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08604118227958679}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7824851274490356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272371053695679},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6985481977462769},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6787448525428772},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5326604247093201},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5299690365791321},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5055649280548096},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4449479579925537},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.43618154525756836},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43099427223205566},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4122703969478607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3573368787765503},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13678476214408875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10596504807472229},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08604118227958679},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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":1,"locations":[{"id":"doi:10.1109/lra.2020.2972862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2972862","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W90946604","https://openalex.org/W206679605","https://openalex.org/W1521003796","https://openalex.org/W2046376809","https://openalex.org/W2088956500","https://openalex.org/W2155027007","https://openalex.org/W2395575420","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2786303200","https://openalex.org/W2810602713","https://openalex.org/W2892258706","https://openalex.org/W2912971983","https://openalex.org/W2913845934","https://openalex.org/W2962938168","https://openalex.org/W2963000099","https://openalex.org/W2963407617","https://openalex.org/W2963881016","https://openalex.org/W2964338167","https://openalex.org/W3099518626","https://openalex.org/W3103532359","https://openalex.org/W3103635569","https://openalex.org/W4299802797","https://openalex.org/W6631137000","https://openalex.org/W6683204974","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6735650757","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6747993910"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2768698792","https://openalex.org/W2928233854","https://openalex.org/W2570940879","https://openalex.org/W2889555279"],"abstract_inverted_index":{"Decentralized":[0],"multi-agent":[1,147],"reinforcement":[2],"learning":[3,82],"has":[4,124],"been":[5,69],"demonstrated":[6],"to":[7,12,47,58,71,73,77,98,112],"be":[8,155],"an":[9,87],"effective":[10],"solution":[11],"large":[13],"multiagent":[14],"control":[15],"problems.":[16],"However,":[17],"agents":[18,46],"typically":[19],"can":[20],"only":[21],"make":[22],"decisions":[23],"based":[24],"on":[25,144,185],"local":[26],"information,":[27],"resulting":[28],"in":[29,32,151,169],"suboptimal":[30],"performance":[31],"partially-observable":[33],"settings.":[34],"The":[35],"addition":[36],"of":[37,64,81,108,140,177],"a":[38,114,125,145],"communication":[39],"channel":[40],"overcomes":[41],"this":[42],"limitation":[43],"by":[44,180],"allowing":[45],"exchange":[48],"information.":[49],"Existing":[50],"approaches,":[51],"however,":[52],"have":[53,68],"required":[54],"agent":[55,95],"output":[56,96],"size":[57,97],"scale":[59,99],"exponentially":[60],"with":[61,101],"the":[62,78,109,138,175,182],"number":[63],"message":[65,83,90,128],"bits,":[66],"and":[67,123,167,173],"slow":[70],"converge":[72],"satisfactory":[74],"policies":[75,184],"due":[76],"added":[79],"difficulty":[80],"selection.":[84],"We":[85,136,159],"propose":[86],"independent":[88],"bitwise":[89],"policy":[91,116,133],"parameterization":[92],"that":[93,119,161],"allows":[94],"linearly":[100],"information":[102,153],"content.":[103],"Additionally,":[104],"we":[105],"leverage":[106],"aspects":[107],"environment":[110],"structure":[111],"derive":[113],"novel":[115],"gradient":[117,129,134],"estimator":[118],"is":[120],"both":[121,162],"unbiased":[122],"lower":[126],"variance":[127],"contribution":[130],"than":[131],"typical":[132],"estimators.":[135],"evaluate":[137],"impact":[139],"these":[141,178],"two":[142],"contributions":[143],"collaborative":[146],"robot":[148],"navigation":[149],"problem,":[150],"which":[152],"must":[154],"exchanged":[156],"among":[157],"agents.":[158],"find":[160],"significantly":[163],"improve":[164],"sample":[165],"efficiency":[166],"result":[168],"improved":[170],"final":[171],"policies,":[172],"demonstrate":[174],"applicability":[176],"techniques":[179],"deploying":[181],"learned":[183],"physical":[186],"robots.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}