{"id":"https://openalex.org/W7124258685","doi":"https://doi.org/10.65109/iuhq8304","title":"Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning","display_name":"Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W7124258685","doi":"https://doi.org/10.65109/iuhq8304"},"language":"en","primary_location":{"id":"doi:10.65109/iuhq8304","doi":"https://doi.org/10.65109/iuhq8304","is_oa":false,"landing_page_url":"https://doi.org/10.65109/iuhq8304","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.03972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093895845","display_name":"Maxime Toquebiau","orcid":"https://orcid.org/0000-0003-2304-9467","observed_orcids":["https://orcid.org/0000-0003-2304-9467"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210116658","display_name":"\u00c9cole Centrale d'\u00c9lectronique","ror":"https://ror.org/02k6n4s14","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210116658"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maxime Toquebiau","raw_affiliation_strings":["ECE Paris & Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Paris & Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210116658","https://openalex.org/I4210150358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008211251","display_name":"Nicolas Bred\u00e8che","orcid":"https://orcid.org/0000-0002-8241-7461","observed_orcids":["https://orcid.org/0000-0002-8241-7461"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Bredeche","raw_affiliation_strings":["Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035441826","display_name":"Fa\u00efz Ben Amar","orcid":"https://orcid.org/0000-0002-4590-3452","observed_orcids":["https://orcid.org/0000-0002-4590-3452"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fa\u00efz Benamar","raw_affiliation_strings":["Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015477108","display_name":"Jae\u2010Yun Jun","orcid":"https://orcid.org/0000-0002-4651-8978","observed_orcids":["https://orcid.org/0000-0002-4651-8978"]},"institutions":[{"id":"https://openalex.org/I4210116658","display_name":"\u00c9cole Centrale d'\u00c9lectronique","ror":"https://ror.org/02k6n4s14","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210116658"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jae-Yun Jun","raw_affiliation_strings":["ECE Paris, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Paris, Paris, France","institution_ids":["https://openalex.org/I4210116658"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3054,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50447172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2522","last_page":"2524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.0,"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/multi-agent-deep-reinforcement-learning","display_name":"multi-agent deep reinforcement learning","score":0.9210000038146973},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"intrinsic motivation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"novelty detection","score":0.5410000085830688},{"id":"https://openalex.org/keywords/multiagent-coordination","display_name":"multi-agent coordination","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7494000196456909},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555400013923645},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49549999833106995},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2727000117301941},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.24369999766349792}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.65109/iuhq8304","doi":"https://doi.org/10.65109/iuhq8304","is_oa":false,"landing_page_url":"https://doi.org/10.65109/iuhq8304","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.03972","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.03972","pdf_url":"https://arxiv.org/pdf/2402.03972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05734661v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-05734661v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2024, Auckland, New Zealand","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2402.03972","doi":"https://doi.org/10.48550/arxiv.2402.03972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.03972","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.03972","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.03972","pdf_url":"https://arxiv.org/pdf/2402.03972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124258685.pdf","grobid_xml":"https://content.openalex.org/works/W7124258685.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2000514530","https://openalex.org/W2530849036","https://openalex.org/W2798511001","https://openalex.org/W2947526499","https://openalex.org/W2996037775","https://openalex.org/W4300630456","https://openalex.org/W7133226216"],"related_works":["https://openalex.org/W4403296108","https://openalex.org/W4393156968","https://openalex.org/W3198127929","https://openalex.org/W3170511602","https://openalex.org/W7206157772","https://openalex.org/W2947526499","https://openalex.org/W4409581282","https://openalex.org/W7124246568","https://openalex.org/W3211360571","https://openalex.org/W4385488901"],"abstract_inverted_index":{"Multi-agent":[0],"deep":[1],"reinforcement":[2],"learning":[3],"(MADRL)":[4],"often":[5],"struggles":[6],"to":[7,45,96],"learn":[8],"strongly":[9],"coordinated":[10,104,111],"tasks,":[11],"as":[12],"performance":[13],"depends":[14],"not":[15],"only":[16],"on":[17,23,83],"one":[18],"agent's":[19],"behavior":[20,26],"but":[21],"rather":[22],"the":[24,47,107],"joint":[25,43,80],"of":[27,35,87,110],"multiple":[28],"agents.":[29],"In":[30,51],"this":[31,52],"context,":[32],"a":[33,73,84,102],"group":[34],"agents":[36,62],"can":[37,93],"benefit":[38],"from":[39],"actively":[40],"exploring":[41],"different":[42],"strategies":[44,60],"determine":[46],"most":[48],"efficient":[49],"one.":[50],"paper,":[53],"we":[54],"propose":[55],"an":[56],"approach":[57],"for":[58],"rewarding":[59],"where":[61],"collectively":[63],"exhibit":[64],"novel":[65],"behaviors.":[66],"We":[67,89],"present":[68],"JIM":[69,92],"(Joint":[70],"Intrinsic":[71],"Motivation),":[72],"multi-agent":[74],"intrinsic":[75],"motivation":[76],"method":[77],"that":[78],"rewards":[79],"trajectories":[81],"based":[82],"centralized":[85],"measure":[86],"novelty.":[88],"show":[90],"how":[91],"be":[94],"used":[95],"improve":[97],"state-of-the-art":[98],"MADRL":[99],"methods":[100],"in":[101],"highly":[103],"task,":[105],"demonstrating":[106],"crucial":[108],"role":[109],"exploration.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-01-16T00:00:00"}