{"id":"https://openalex.org/W2971027212","doi":"https://doi.org/10.1007/s10994-019-05864-5","title":"Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication","display_name":"Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication","publication_year":2020,"publication_date":"2020-01-23","ids":{"openalex":"https://openalex.org/W2971027212","doi":"https://doi.org/10.1007/s10994-019-05864-5","mag":"2971027212"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05864-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05864-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05864-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05864-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Emanuele Pesce","orcid":"https://orcid.org/0000-0002-0314-8057"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Emanuele Pesce","raw_affiliation_strings":["WMG, University of Warwick, Coventry, CV4 7AL, UK"],"raw_orcid":"https://orcid.org/0000-0002-0314-8057","affiliations":[{"raw_affiliation_string":"WMG, University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":null,"display_name":"Giovanni Montana","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giovanni Montana","raw_affiliation_strings":["WMG, University of Warwick, Coventry, CV4 7AL, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WMG, University of Warwick, Coventry, CV4 7AL, UK","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39555362"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.4,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.93631325,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"109","issue":"9-10","first_page":"1727","last_page":"1747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.722100019454956,"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":0.722100019454956,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.04430000111460686,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.026100000366568565,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8206999897956848},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6539000272750854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/communications-protocol","display_name":"Communications protocol","score":0.45649999380111694},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4433000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259999752044678},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8206999897956848},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6539000272750854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5346999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5307000279426575},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5055999755859375},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41019999980926514},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-019-05864-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05864-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05864-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1901.03887","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.03887","pdf_url":"https://arxiv.org/pdf/1901.03887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05864-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05864-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05864-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320279","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2971027212.pdf","grobid_xml":"https://content.openalex.org/works/W2971027212.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1518858799","https://openalex.org/W1541084404","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1574700590","https://openalex.org/W1579184372","https://openalex.org/W1641379095","https://openalex.org/W1964644919","https://openalex.org/W1964883026","https://openalex.org/W1977136897","https://openalex.org/W1985955147","https://openalex.org/W1986268386","https://openalex.org/W1997881026","https://openalex.org/W1997932767","https://openalex.org/W2005636787","https://openalex.org/W2011751276","https://openalex.org/W2017957151","https://openalex.org/W2034184326","https://openalex.org/W2034692547","https://openalex.org/W2039533720","https://openalex.org/W2048519937","https://openalex.org/W2059529072","https://openalex.org/W2064675550","https://openalex.org/W2066866890","https://openalex.org/W2076063813","https://openalex.org/W2089773578","https://openalex.org/W2106701811","https://openalex.org/W2107544712","https://openalex.org/W2108892923","https://openalex.org/W2124141629","https://openalex.org/W2126087036","https://openalex.org/W2127397140","https://openalex.org/W2128453677","https://openalex.org/W2136696289","https://openalex.org/W2139232530","https://openalex.org/W2145339207","https://openalex.org/W2147667317","https://openalex.org/W2148831627","https://openalex.org/W2151389381","https://openalex.org/W2160643434","https://openalex.org/W2165321212","https://openalex.org/W2173200640","https://openalex.org/W2173248099","https://openalex.org/W2179488730","https://openalex.org/W2290526371","https://openalex.org/W2292533394","https://openalex.org/W2395575420","https://openalex.org/W2402402867","https://openalex.org/W2496794451","https://openalex.org/W2586491110","https://openalex.org/W2623431351","https://openalex.org/W2625978909","https://openalex.org/W2768629321","https://openalex.org/W2778610932","https://openalex.org/W2894976951","https://openalex.org/W2906394285","https://openalex.org/W2907606902","https://openalex.org/W2919115771","https://openalex.org/W2951276827","https://openalex.org/W2963658727","https://openalex.org/W3121507878","https://openalex.org/W6635285615","https://openalex.org/W6638018090","https://openalex.org/W6677834374","https://openalex.org/W6684205842","https://openalex.org/W6756040250"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"reinforcement":[2],"learning":[3,66,102],"algorithms":[4],"have":[5],"recently":[6],"been":[7],"used":[8],"to":[9,81,89,134],"train":[10],"multiple":[11],"interacting":[12],"agents":[13,25,79],"in":[14,116,130],"a":[15,52,73,91,163],"centralised":[16],"manner":[17],"whilst":[18],"keeping":[19],"their":[20],"execution":[21],"decentralised.":[22],"When":[23],"the":[24,78,95,104,124,155,159,166,171,179,183],"can":[26,110,143],"only":[27],"acquire":[28],"partial":[29],"observations":[30],"and":[31,38,84,107,114,177],"are":[32],"faced":[33],"with":[34,132],"tasks":[35,148],"requiring":[36],"coordination":[37,113],"synchronisation":[39],"skills,":[40],"inter-agent":[41,112],"communication":[42,70,105,141,160],"plays":[43],"an":[44,68],"essential":[45],"role.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,153],"propose":[51],"framework":[53],"for":[54],"multi-agent":[55],"training":[56],"using":[57],"deep":[58],"deterministic":[59],"policy":[60],"gradients":[61],"that":[62,100,123],"enables":[63],"concurrent,":[64],"end-to-end":[65],"of":[67,94,103,149,157,165,182],"explicit":[69],"protocol":[71],"through":[72,187],"memory":[74,168,185],"device.":[75],"During":[76],"training,":[77],"learn":[80],"perform":[82],"read":[83],"write":[85],"operations":[86],"enabling":[87],"them":[88],"infer":[90],"shared":[92],"representation":[93],"world.":[96],"We":[97,137],"empirically":[98],"demonstrate":[99],"concurrent":[101],"device":[106,186],"individual":[108],"policies":[109],"improve":[111],"performance":[115,129],"small-scale":[117],"systems.":[118],"Our":[119],"experimental":[120],"results":[121],"show":[122],"proposed":[125,184],"method":[126],"achieves":[127],"superior":[128],"scenarios":[131],"up":[133],"six":[135,146],"agents.":[136],"illustrate":[138],"how":[139],"different":[140,147],"patterns":[142],"emerge":[144],"on":[145],"increasing":[150],"complexity.":[151],"Furthermore,":[152],"study":[154],"effects":[156],"corrupting":[158],"channel,":[161],"provide":[162],"visualisation":[164],"time-varying":[167],"content":[169],"as":[170],"underlying":[172],"task":[173],"is":[174],"being":[175],"solved":[176],"validate":[178],"building":[180],"blocks":[181],"ablation":[188],"studies.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2019-09-05T00:00:00"}