{"id":"https://openalex.org/W4401414918","doi":"https://doi.org/10.1109/icra57147.2024.10610745","title":"POAQL: A Partially Observable Altruistic Q-Learning Method for Cooperative Multi-Agent Reinforcement Learning","display_name":"POAQL: A Partially Observable Altruistic Q-Learning Method for Cooperative Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414918","doi":"https://doi.org/10.1109/icra57147.2024.10610745"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610745","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5039148038","display_name":"Lesong Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Lesong Tao","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082298742","display_name":"Miao Kang","orcid":"https://orcid.org/0000-0002-4382-5796"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Miao Kang","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004232422","display_name":"Jinpeng Dong","orcid":"https://orcid.org/0009-0006-6938-4315"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jinpeng Dong","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048544277","display_name":"Songyi Zhang","orcid":"https://orcid.org/0000-0002-5776-0858"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Songyi Zhang","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101254928","display_name":"Ke Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Ke Ye","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774271","display_name":"Shitao Chen","orcid":"https://orcid.org/0000-0002-9422-3058"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Shitao Chen","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics","institution_ids":["https://openalex.org/I4210105595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5039148038"],"corresponding_institution_ids":["https://openalex.org/I4210105595"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10590734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"15076","last_page":"15082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10524","display_name":"Traffic control and management","score":0.9822999835014343,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9643999934196472,"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/q-learning","display_name":"Q-learning","score":0.8600033521652222},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8555108308792114},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.688873291015625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6067096590995789},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5236353874206543},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.521766722202301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36432909965515137},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1308169960975647},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10121792554855347},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06473985314369202}],"concepts":[{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.8600033521652222},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8555108308792114},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.688873291015625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067096590995789},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5236353874206543},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.521766722202301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36432909965515137},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1308169960975647},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10121792554855347},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06473985314369202},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610745","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W1488757178","https://openalex.org/W1522301498","https://openalex.org/W1549280300","https://openalex.org/W1641379095","https://openalex.org/W1973396716","https://openalex.org/W1989407213","https://openalex.org/W2145339207","https://openalex.org/W2296073425","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2730530972","https://openalex.org/W2892258706","https://openalex.org/W2903998385","https://openalex.org/W2913211223","https://openalex.org/W2963762747","https://openalex.org/W2968526727","https://openalex.org/W3012544020","https://openalex.org/W3037164939","https://openalex.org/W3092786062","https://openalex.org/W3103635569","https://openalex.org/W3133734443","https://openalex.org/W3156295478","https://openalex.org/W3175724379","https://openalex.org/W3206082228","https://openalex.org/W4212774754","https://openalex.org/W6625145268","https://openalex.org/W6631190155","https://openalex.org/W6632662516","https://openalex.org/W6640212811","https://openalex.org/W6685444567","https://openalex.org/W6693839119","https://openalex.org/W6739516088","https://openalex.org/W6744401026","https://openalex.org/W6754689381","https://openalex.org/W6758754608","https://openalex.org/W6762491519","https://openalex.org/W6763563180","https://openalex.org/W6766805167","https://openalex.org/W6775683342"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692"],"abstract_inverted_index":{"Multi-Agent":[0],"Path":[1],"Finding":[2],"(MAPF)":[3],"is":[4,30,45],"an":[5,90],"important":[6,91],"issue":[7],"in":[8,21,38,93,128],"multi-agent":[9],"cooperation.":[10],"Many":[11],"studies":[12],"apply":[13],"MultiAgent":[14],"Reinforcement":[15],"Learning":[16],"(MARL)":[17],"to":[18,31,48,110],"solve":[19],"MAPF":[20],"partially":[22,39],"observable":[23,40],"settings.":[24],"The":[25],"objective":[26],"of":[27,56,77,82,115,130],"cooperative":[28,113],"MARL":[29,116],"maximize":[32],"the":[33,42,52,74,78,83,95,112],"cumulative":[34,75],"team":[35,43],"reward.":[36],"Nevertheless,":[37],"settings,":[41],"reward":[44,76],"misleading":[46],"due":[47],"unpredictable":[49],"factors":[50],"from":[51],"behavior":[53],"and":[54,132],"state":[55],"unobserved":[57],"agents.":[58],"To":[59],"address":[60],"this":[61],"issue,":[62],"we":[63,101],"propose":[64],"a":[65,103],"Partially":[66],"Observable":[67],"Altruistic":[68,87],"Q-learning":[69,88],"(POAQL)":[70],"method.":[71],"POAQL":[72,122],"considers":[73],"observed":[79],"subteam":[80,96],"instead":[81],"whole":[84],"team,":[85],"where":[86],"plays":[89],"role":[92],"learning":[94,126],"action":[97],"value.":[98],"In":[99],"addition,":[100],"design":[102],"new":[104],"conflict":[105],"resolution":[106],"without":[107],"additional":[108],"guidance":[109],"emphasize":[111],"nature":[114],"frameworks.":[117],"Experimental":[118],"results":[119],"show":[120],"that":[121],"outperforms":[123],"existing":[124],"reinforcement":[125],"methods":[127],"terms":[129],"efficiency":[131],"performance.":[133]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}