{"id":"https://openalex.org/W3132143885","doi":"https://doi.org/10.1109/iros45743.2020.9341079","title":"Sparse Discrete Communication Learning for Multi-Agent Cooperation Through Backpropagation","display_name":"Sparse Discrete Communication Learning for Multi-Agent Cooperation Through Backpropagation","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3132143885","doi":"https://doi.org/10.1109/iros45743.2020.9341079","mag":"3132143885"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/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, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001522086","display_name":"Rohan James","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":"Rohan James","raw_affiliation_strings":["Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, 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":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of 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, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute at Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081604594"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79328277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.991599977016449,"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":0.979200005531311,"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/computer-science","display_name":"Computer science","score":0.7777622938156128},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5855448842048645},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.563020646572113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49192094802856445},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.49061718583106995},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4715944230556488},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44898349046707153},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35908448696136475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34044623374938965},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28084248304367065},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0864487886428833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07264760136604309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777622938156128},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5855448842048645},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.563020646572113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49192094802856445},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.49061718583106995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4715944230556488},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44898349046707153},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35908448696136475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34044623374938965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28084248304367065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0864487886428833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07264760136604309},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W84899576","https://openalex.org/W1641379095","https://openalex.org/W1684361744","https://openalex.org/W2156737235","https://openalex.org/W2395575420","https://openalex.org/W2602275733","https://openalex.org/W2604382266","https://openalex.org/W2810602713","https://openalex.org/W2892258706","https://openalex.org/W2898035736","https://openalex.org/W2908261578","https://openalex.org/W2912971983","https://openalex.org/W2951542323","https://openalex.org/W2963000099","https://openalex.org/W2963407617","https://openalex.org/W2963658727","https://openalex.org/W2963881016","https://openalex.org/W2964338167","https://openalex.org/W2969052628","https://openalex.org/W2970315248","https://openalex.org/W2973525135","https://openalex.org/W2997556607","https://openalex.org/W3005657850","https://openalex.org/W3099518626","https://openalex.org/W3103532359","https://openalex.org/W3103635569","https://openalex.org/W4211008118","https://openalex.org/W4299802797","https://openalex.org/W4301311528","https://openalex.org/W6683195989","https://openalex.org/W6685388067","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6757214667","https://openalex.org/W6761632846","https://openalex.org/W6767919266"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4239286941","https://openalex.org/W4327738859","https://openalex.org/W2088845016","https://openalex.org/W589102260","https://openalex.org/W1966421350","https://openalex.org/W1868434454","https://openalex.org/W4366984740","https://openalex.org/W2348722996","https://openalex.org/W4366985237"],"abstract_inverted_index":{"Recent":[0],"approaches":[1],"to":[2,31,48,81],"multi-agent":[3],"reinforcement":[4],"learning":[5,32,113,134],"(MARL)":[6],"with":[7,101],"inter-agent":[8],"communication":[9,17,35,69,137,155],"have":[10],"often":[11],"overlooked":[12],"important":[13],"considerations":[14],"of":[15,41,62,105,135,159],"real-world":[16],"networks,":[18],"such":[19],"as":[20,50,52],"limits":[21],"on":[22,60,66,120],"bandwidth.":[23],"In":[24],"this":[25,90],"paper,":[26],"we":[27,71,92,127],"propose":[28],"an":[29,152,160],"approach":[30,132,148],"sparse":[33,136,154],"discrete":[34,68],"through":[36],"backpropagation":[37],"in":[38,43],"the":[39,111,142],"context":[40],"MARL,":[42],"which":[44],"agents":[45,80,100],"are":[46],"incentivized":[47],"communicate":[49],"little":[51],"possible":[53],"while":[54,109,139],"still":[55,140],"achieving":[56],"high":[57],"reward.":[58],"Building":[59],"top":[61],"our":[63,131,147],"prior":[64],"work":[65],"differentiable":[67],"learning,":[70],"develop":[72],"a":[73,94,102,121],"regularization-inspired":[74],"message-length":[75],"penalty":[76],"term,":[77],"that":[78,98],"encourages":[79],"send":[82],"shorter":[83],"messages":[84],"and":[85],"avoid":[86],"unnecessary":[87],"communications.":[88],"To":[89],"end,":[91],"introduce":[93],"variable-length":[95],"message":[96,107],"code":[97],"provides":[99],"general":[103],"means":[104],"modulating":[106],"length":[108],"keeping":[110],"overall":[112],"objective":[114],"differentiable.":[115],"We":[116,144],"present":[117],"simulation":[118],"results":[119],"partially-observable":[122],"robot":[123],"navigation":[124],"task,":[125],"where":[126],"first":[128],"show":[129],"how":[130],"allows":[133],"behavior":[138,156],"solving":[141],"task.":[143],"finally":[145],"demonstrate":[146],"can":[149],"even":[150],"learn":[151],"effective":[153],"from":[157],"demonstrations":[158],"expert":[161],"(potentially":[162],"communication-free)":[163],"policy.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
