{"id":"https://openalex.org/W4407200586","doi":"https://doi.org/10.1007/s10994-024-06700-1","title":"Toward finding strong pareto optimal policies in multi-agent reinforcement learning","display_name":"Toward finding strong pareto optimal policies in multi-agent reinforcement learning","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407200586","doi":"https://doi.org/10.1007/s10994-024-06700-1"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06700-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10994-024-06700-1","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","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/A5077010288","display_name":"Bang Giang Le","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Bang Giang Le","raw_affiliation_strings":["Human Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, 100000, Vietnam"],"affiliations":[{"raw_affiliation_string":"Human Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210128676"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053935756","display_name":"Viet Cuong Ta","orcid":"https://orcid.org/0000-0001-8058-5915"},"institutions":[{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Viet Cuong Ta","raw_affiliation_strings":["Human Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, 100000, Vietnam"],"affiliations":[{"raw_affiliation_string":"Human Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210128676"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077010288"],"corresponding_institution_ids":["https://openalex.org/I4210128676"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":5.399,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94379571,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"114","issue":"3","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":0.9995999932289124,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9883000254631042,"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"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8776415586471558},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6307511329650879},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5545910596847534},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.5170713067054749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5075870752334595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4221500754356384},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3966107666492462},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29013654589653015},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.23543819785118103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22213459014892578},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1712808907032013},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11303365230560303}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8776415586471558},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6307511329650879},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5545910596847534},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.5170713067054749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5075870752334595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221500754356384},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3966107666492462},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29013654589653015},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.23543819785118103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22213459014892578},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1712808907032013},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11303365230560303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-024-06700-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10994-024-06700-1","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1631817276","display_name":null,"funder_award_id":"FA2386-24-1-4012","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1641379095","https://openalex.org/W2019792531","https://openalex.org/W2060727197","https://openalex.org/W2100717205","https://openalex.org/W2623431351","https://openalex.org/W2763081248","https://openalex.org/W2889351029","https://openalex.org/W2890538051","https://openalex.org/W2922170773","https://openalex.org/W2963658727","https://openalex.org/W2963762747","https://openalex.org/W2990138404","https://openalex.org/W3186349061","https://openalex.org/W4214717370","https://openalex.org/W4286748781","https://openalex.org/W4312084516","https://openalex.org/W4378942319","https://openalex.org/W4386270404","https://openalex.org/W6767140673","https://openalex.org/W6771876938"],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W2080708212","https://openalex.org/W2337862504","https://openalex.org/W2043126582","https://openalex.org/W317165722","https://openalex.org/W2728870795"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}