{"id":"https://openalex.org/W2987204115","doi":"https://doi.org/10.1080/01969722.2019.1677335","title":"When Does Communication Learning Need Hierarchical Multi-Agent Deep Reinforcement Learning","display_name":"When Does Communication Learning Need Hierarchical Multi-Agent Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2987204115","doi":"https://doi.org/10.1080/01969722.2019.1677335","mag":"2987204115"},"language":"en","primary_location":{"id":"doi:10.1080/01969722.2019.1677335","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01969722.2019.1677335","pdf_url":null,"source":{"id":"https://openalex.org/S117436046","display_name":"Cybernetics & Systems","issn_l":"0196-9722","issn":["0196-9722","1087-6553"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybernetics and Systems","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/A5005962214","display_name":"Marie Ossenkopf","orcid":null},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marie Ossenkopf","raw_affiliation_strings":["Distributed Systems Group, University of Kassel, Kassel, Germany;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Systems Group, University of Kassel, Kassel, Germany;","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025026852","display_name":"Mackenzie Jorgensen","orcid":"https://orcid.org/0009-0001-1274-1733"},"institutions":[{"id":"https://openalex.org/I7863295","display_name":"Villanova University","ror":"https://ror.org/02g7kd627","country_code":"US","type":"education","lineage":["https://openalex.org/I7863295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mackenzie Jorgensen","raw_affiliation_strings":["Computing Sciences, Villanova University, Villanova, Pennsylvania, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Sciences, Villanova University, Villanova, Pennsylvania, USA","institution_ids":["https://openalex.org/I7863295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077860593","display_name":"Kurt Geihs","orcid":"https://orcid.org/0000-0001-9833-6108"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kurt Geihs","raw_affiliation_strings":["Distributed Systems Group, University of Kassel, Kassel, Germany;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Systems Group, University of Kassel, Kassel, Germany;","institution_ids":["https://openalex.org/I106157433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005962214"],"corresponding_institution_ids":["https://openalex.org/I106157433"],"apc_list":null,"apc_paid":null,"fwci":0.6317,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78087337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"50","issue":"8","first_page":"672","last_page":"692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.960099995136261,"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":0.8519421219825745},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8463817834854126},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.801368236541748},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6727595329284668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.56662517786026},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5471710562705994},{"id":"https://openalex.org/keywords/communications-protocol","display_name":"Communications protocol","score":0.4578707218170166},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.45452582836151123},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43441396951675415},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4279567301273346},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3435707688331604},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16871455311775208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519421219825745},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8463817834854126},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.801368236541748},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6727595329284668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56662517786026},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5471710562705994},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.4578707218170166},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.45452582836151123},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43441396951675415},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4279567301273346},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3435707688331604},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16871455311775208},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/01969722.2019.1677335","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01969722.2019.1677335","pdf_url":null,"source":{"id":"https://openalex.org/S117436046","display_name":"Cybernetics & Systems","issn_l":"0196-9722","issn":["0196-9722","1087-6553"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybernetics and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1969302761","https://openalex.org/W2064675550","https://openalex.org/W2069143585","https://openalex.org/W2107878631","https://openalex.org/W2145339207","https://openalex.org/W2166302491","https://openalex.org/W2257979135","https://openalex.org/W2335959470","https://openalex.org/W2395575420","https://openalex.org/W2402402867","https://openalex.org/W2464608064","https://openalex.org/W2559655401","https://openalex.org/W2562637642","https://openalex.org/W2756196406","https://openalex.org/W2776126823","https://openalex.org/W2781238083","https://openalex.org/W2790405363","https://openalex.org/W2803155336","https://openalex.org/W2913654295","https://openalex.org/W2943368604","https://openalex.org/W2962852262","https://openalex.org/W4212774754","https://openalex.org/W6719467079"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2388330702","https://openalex.org/W4298212052","https://openalex.org/W2409714959","https://openalex.org/W2392986374","https://openalex.org/W2107737506","https://openalex.org/W2390164899","https://openalex.org/W4254015142"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1,64],"need":[2],"to":[3,5,29],"communicate":[4],"coordinate":[6,30],"a":[7,13,20,41,56,77,85,97],"shared":[8],"task.":[9],"We":[10,38,54,80,114],"show":[11,39],"that":[12,40,65,84],"recurrent":[14],"neural":[15],"network":[16],"(RNN)":[17],"can":[18],"learn":[19],"communication":[21,36,68,90],"protocol":[22],"for":[23,51,62],"coordination,":[24],"even":[25],"if":[26],"the":[27,35,67,73,101,108,124],"actions":[28],"are":[31],"performed":[32],"steps":[33],"after":[34],"phase.":[37],"separation":[42,86],"of":[43,87],"tasks":[44],"with":[45],"different":[46,120],"temporal":[47],"scale":[48],"is":[49,91],"necessary":[50],"successful":[52],"learning.":[53],"contribute":[55],"hierarchical":[57,78],"deep":[58],"reinforcement":[59],"learning":[60],"model":[61,121],"multi-agent":[63],"separates":[66],"and":[69,105,116],"coordination":[70],"task":[71],"from":[72,119],"action":[74],"picking":[75],"through":[76],"policy.":[79],"further":[81],"on":[82,123],"show,":[83],"concerns":[88],"in":[89],"beneficial":[92],"but":[93],"not":[94],"necessary.":[95],"As":[96],"testbed,":[98],"we":[99,106],"propose":[100],"Dungeon":[102,125],"Lever":[103,126],"Game":[104],"extend":[107],"Differentiable":[109],"Inter-Agent":[110],"Learning":[111],"(DIAL)":[112],"framework.":[113],"present":[115],"compare":[117],"results":[118],"variations":[122],"Game.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}
