{"id":"https://openalex.org/W4294266558","doi":"https://doi.org/10.3233/aic-220116","title":"Deep reinforcement learning for multi-agent interaction","display_name":"Deep reinforcement learning for multi-agent interaction","publication_year":2022,"publication_date":"2022-09-02","ids":{"openalex":"https://openalex.org/W4294266558","doi":"https://doi.org/10.3233/aic-220116"},"language":"en","primary_location":{"id":"doi:10.3233/aic-220116","is_oa":false,"landing_page_url":"https://doi.org/10.3233/aic-220116","pdf_url":null,"source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","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/A5100743339","display_name":"Ibrahim Ahmed","orcid":"https://orcid.org/0000-0003-1510-4219"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ibrahim H. Ahmed","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021143655","display_name":"Cillian Brewitt","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cillian Brewitt","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088668090","display_name":"Ignacio Carlucho","orcid":"https://orcid.org/0000-0002-6262-480X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ignacio Carlucho","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047256432","display_name":"Filippos Christianos","orcid":"https://orcid.org/0000-0002-4230-2846"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Filippos Christianos","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014910172","display_name":"Mhairi Dunion","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mhairi Dunion","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054799209","display_name":"Elliot Fosong","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elliot Fosong","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058892062","display_name":"Samuel Garcin","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samuel Garcin","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065424581","display_name":"Shangmin Guo","orcid":"https://orcid.org/0000-0003-1716-0994"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shangmin Guo","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069295532","display_name":"B\u00e1lint Gyevn\u00e1r","orcid":"https://orcid.org/0000-0003-0630-4315"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Balint Gyevnar","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075574083","display_name":"Trevor McInroe","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Trevor McInroe","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038910835","display_name":"Georgios Papoudakis","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Papoudakis","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074220260","display_name":"Arrasy Rahman","orcid":"https://orcid.org/0000-0003-1006-9653"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arrasy Rahman","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068676054","display_name":"Lukas Sch\u00e4fer","orcid":"https://orcid.org/0000-0002-4335-9342"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lukas Sch\u00e4fer","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087191252","display_name":"Massimiliano Tamborski","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Massimiliano Tamborski","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055647763","display_name":"Giuseppe Vecchio","orcid":"https://orcid.org/0000-0001-5009-4365"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giuseppe Vecchio","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417008","display_name":"Cheng Wang","orcid":"https://orcid.org/0000-0002-5309-8115"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheng Wang","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073739308","display_name":"Stefano V. Albrecht","orcid":"https://orcid.org/0000-0002-8735-1465"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stefano\u00a0V. Albrecht","raw_affiliation_strings":["Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Agents Research Group, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5073739308"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.0808,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88871442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"4","first_page":"357","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9470000267028809,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9071999788284302,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8483214974403381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8244690895080566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6760631203651428},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5017414093017578},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43518972396850586},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4256017208099365},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.423331618309021},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.41818055510520935}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8483214974403381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8244690895080566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6760631203651428},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5017414093017578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43518972396850586},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4256017208099365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.423331618309021},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.41818055510520935},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/aic-220116","is_oa":false,"landing_page_url":"https://doi.org/10.3233/aic-220116","pdf_url":null,"source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1606056663","https://openalex.org/W2000514530","https://openalex.org/W2188721763","https://openalex.org/W2566823413","https://openalex.org/W2605102758","https://openalex.org/W2758442112","https://openalex.org/W2915117209","https://openalex.org/W3025440712","https://openalex.org/W3035305488","https://openalex.org/W3093853968","https://openalex.org/W3114563362","https://openalex.org/W3118240751","https://openalex.org/W3134269141","https://openalex.org/W3170300491","https://openalex.org/W3187402175","https://openalex.org/W3189552233","https://openalex.org/W3204745744","https://openalex.org/W4250731795","https://openalex.org/W4312867245"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2041126907","https://openalex.org/W2494202692"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,20,62,76,102,107],"autonomous":[3,42],"agents":[4,10,78],"which":[5],"can":[6],"interact":[7],"with":[8,45],"other":[9,77],"to":[11],"accomplish":[12],"a":[13,17,46,99],"given":[14],"task":[15],"is":[16],"core":[18],"area":[19],"research":[21,105],"in":[22],"artificial":[23],"intelligence":[24],"and":[25,53,66,74,82,93,110],"machine":[26,38],"learning.":[27,56,95],"Towards":[28],"this":[29],"goal,":[30],"the":[31,71,103,108],"Autonomous":[32],"Agents":[33],"Research":[34,57],"Group":[35],"develops":[36],"novel":[37],"learning":[39,52,61,84],"algorithms":[40],"for":[41,114],"systems":[43],"control,":[44],"specific":[47],"focus":[48],"on":[49,86],"deep":[50],"reinforcement":[51,55],"multi-agent":[54],"problems":[58,113],"include":[59],"scalable":[60],"coordinated":[63],"agent":[64],"policies":[65],"inter-agent":[67],"communication;":[68],"reasoning":[69],"about":[70],"behaviours,":[72],"goals,":[73],"composition":[75],"from":[79],"limited":[80],"observations;":[81],"sample-efficient":[83],"based":[85],"intrinsic":[87],"motivation,":[88],"curriculum":[89],"learning,":[90],"causal":[91],"inference,":[92],"representation":[94],"This":[96],"article":[97],"provides":[98],"broad":[100],"overview":[101],"ongoing":[104],"portfolio":[106],"group":[109],"discusses":[111],"open":[112],"future":[115],"directions.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-10T00:00:00"}
