{"id":"https://openalex.org/W4406208044","doi":"https://doi.org/10.1109/icarcv63323.2024.10821634","title":"Assessment of Multi-Agent Reinforcement Learning Strategies for Multi-Agent Negotiation","display_name":"Assessment of Multi-Agent Reinforcement Learning Strategies for Multi-Agent Negotiation","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4406208044","doi":"https://doi.org/10.1109/icarcv63323.2024.10821634"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv63323.2024.10821634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv63323.2024.10821634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-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/A5100413697","display_name":"Hongyi Li","orcid":"https://orcid.org/0000-0002-7590-7411"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hongyi Li","raw_affiliation_strings":["College of Design and Engineering, National University of Singapore,Faculty of Mechanical Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Design and Engineering, National University of Singapore,Faculty of Mechanical Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068973829","display_name":"Ruihang Ji","orcid":"https://orcid.org/0000-0002-8726-5719"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruihang Ji","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore,Singapore,117576"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore,Singapore,117576","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008501506","display_name":"Shuzhi Sam Ge","orcid":"https://orcid.org/0000-0001-5549-312X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuzhi Sam Ge","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore,Singapore,117576"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore,Singapore,117576","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100413697"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70909662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.5221999883651733,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.5221999883651733,"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/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.4862000048160553,"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":0.8400907516479492},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.7947944402694702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7050529718399048},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.532123863697052},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47957462072372437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39739635586738586},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09830966591835022},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06496226787567139},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.039975374937057495}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8400907516479492},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.7947944402694702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050529718399048},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.532123863697052},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47957462072372437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39739635586738586},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09830966591835022},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06496226787567139},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.039975374937057495},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarcv63323.2024.10821634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv63323.2024.10821634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G7717780238","display_name":null,"funder_award_id":"AISG2-GC-2023-007","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G798675537","display_name":null,"funder_award_id":"M23M4a0067","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2014791394","https://openalex.org/W2099618002","https://openalex.org/W2145339207","https://openalex.org/W2768629321","https://openalex.org/W2963658727","https://openalex.org/W2968340082","https://openalex.org/W2991046523","https://openalex.org/W3028726361","https://openalex.org/W3206518075","https://openalex.org/W3206530605","https://openalex.org/W4283704716","https://openalex.org/W4384563452","https://openalex.org/W4399495911","https://openalex.org/W4401414215","https://openalex.org/W4401748203","https://openalex.org/W6638088447","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6800004206"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2069705450","https://openalex.org/W2086122291"],"abstract_inverted_index":{"In":[0],"the":[1,6,32,41,75,95,135,165],"realm":[2],"of":[3,9,34,43,82,109,152,168],"multi-agent":[4,141],"systems,":[5],"effective":[7,166],"coordination":[8],"agents":[10,76,84],"for":[11,143],"manipulation":[12,36],"tasks":[13],"poses":[14],"a":[15,68,78],"significant":[16],"challenge.":[17],"This":[18],"study":[19],"explores":[20],"various":[21],"strategies":[22,127],"aimed":[23],"at":[24],"enhancing":[25],"Multi-agent":[26],"Reinforcement":[27,154],"Learning":[28,155],"(MARL)":[29],"algorithms":[30],"in":[31,94,139,170],"context":[33],"locomotion-based":[35],"tasks.":[37],"We":[38],"systematically":[39],"assess":[40],"performance":[42,114],"these":[44],"strategies,":[45,158],"incorporating":[46],"reward":[47],"shaping":[48],"and":[49,58,121,159],"algorithmic":[50],"variations":[51],"such":[52],"as":[53,103,149],"Proximal":[54],"Policy":[55],"Optimization":[56],"(PPO)":[57],"Advantage":[59],"Actor":[60],"Critic":[61],"(A2C).":[62],"For":[63],"better":[64],"cooperation":[65],"between":[66],"agents,":[67],"prediction":[69],"map":[70,81],"is":[71],"also":[72],"implemented,":[73],"informing":[74],"with":[77,100],"probability":[79],"heat":[80],"other":[83],"based":[85],"on":[86,112],"their":[87],"kinematic":[88],"models.":[89],"The":[90],"experiments":[91],"are":[92],"conducted":[93],"Isaac":[96],"Sim":[97],"simulation":[98],"environment":[99],"Jetbot":[101],"robots":[102],"agents.":[104],"Results":[105],"indicate":[106],"distinct":[107],"impacts":[108],"each":[110],"strategy":[111],"critical":[113],"metrics,":[115],"including":[116],"success":[117],"rates,":[118],"collision":[119],"probabilities,":[120],"overall":[122],"task":[123],"efficiency.":[124],"While":[125],"some":[126],"exhibit":[128],"notable":[129],"improvements,":[130],"others":[131],"reveal":[132],"limitations,":[133],"emphasizing":[134],"nuanced":[136],"challenges":[137],"inherent":[138],"optimizing":[140],"systems":[142],"this":[144],"task.":[145],"These":[146],"findings":[147],"serve":[148],"an":[150],"overview":[151],"current":[153],"(RL)":[156],"optimization":[157],"could":[160],"contribute":[161],"valuable":[162],"insights":[163],"to":[164],"deployment":[167],"RL":[169],"complex,":[171],"collaborative":[172],"robotic":[173],"scenarios.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}