{"id":"https://openalex.org/W4392824688","doi":"https://doi.org/10.1109/tg.2024.3375515","title":"GAILPG: Multiagent Policy Gradient With Generative Adversarial Imitation Learning","display_name":"GAILPG: Multiagent Policy Gradient With Generative Adversarial Imitation Learning","publication_year":2024,"publication_date":"2024-03-14","ids":{"openalex":"https://openalex.org/W4392824688","doi":"https://doi.org/10.1109/tg.2024.3375515"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2024.3375515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2024.3375515","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","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/A5100318314","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-9235-9429"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-9235-9429","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiyi Huang","orcid":"https://orcid.org/0000-0002-1114-5198"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyi Huang","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-1114-5198","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858605","display_name":"Ziming Qiu","orcid":"https://orcid.org/0000-0002-7287-5936"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Qiu","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-7287-5936","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048327458","display_name":"Aiguo Song","orcid":"https://orcid.org/0000-0002-1982-6780"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Song","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China","School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-1982-6780","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8328,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86692915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"62","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919999837875366,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919999837875366,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9650999903678894,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9437999725341797,"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/adversarial-system","display_name":"Adversarial system","score":0.8551075458526611},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7951599359512329},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.787592351436615},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5765861868858337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5235925912857056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4311736524105072},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23054245114326477},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22517910599708557},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07293960452079773}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8551075458526611},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7951599359512329},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.787592351436615},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5765861868858337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5235925912857056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4311736524105072},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23054245114326477},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22517910599708557},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07293960452079773}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2024.3375515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2024.3375515","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G8715754740","display_name":null,"funder_award_id":"20200058069001","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2902982219","https://openalex.org/W2963523627","https://openalex.org/W2982316857","https://openalex.org/W3000757491","https://openalex.org/W3085832734","https://openalex.org/W3093571944","https://openalex.org/W3096831136","https://openalex.org/W3213479977","https://openalex.org/W4233776596","https://openalex.org/W4285782692","https://openalex.org/W4291653308","https://openalex.org/W4312776598","https://openalex.org/W6622487243","https://openalex.org/W6630907848","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6715102896","https://openalex.org/W6718092244","https://openalex.org/W6728155968","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6740801417","https://openalex.org/W6745347688","https://openalex.org/W6753207554","https://openalex.org/W6754484421","https://openalex.org/W6755326576","https://openalex.org/W6756303580","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6763150730","https://openalex.org/W6766805167","https://openalex.org/W6771807793","https://openalex.org/W6771968188","https://openalex.org/W6780768476","https://openalex.org/W6781750019","https://openalex.org/W6783838878","https://openalex.org/W6784178060","https://openalex.org/W6786364697","https://openalex.org/W6787511818","https://openalex.org/W6796436736","https://openalex.org/W6797064975","https://openalex.org/W6803709789","https://openalex.org/W6810604644","https://openalex.org/W6840380725","https://openalex.org/W7020879021"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2502115930"],"abstract_inverted_index":{"In":[0],"reinforcement":[1,63],"learning,":[2],"the":[3,9,14,19,22,30,38,44,51,93,99,107,119,123,128,146,150,154,157,161],"agents":[4,48],"need":[5],"to":[6,21,97,117],"sufficiently":[7],"explore":[8],"environment":[10],"and":[11,32,49,140,160],"efficiently":[12],"exploit":[13],"existing":[15],"experiences":[16,55],"before":[17],"finding":[18],"solution":[20],"tasks,":[23],"particularly":[24],"in":[25,60,165],"cooperative":[26,61],"multi-agent":[27,62,94],"scenarios":[28],"where":[29],"state":[31],"action":[33],"spaces":[34],"grow":[35],"exponentially":[36],"with":[37,145],"number":[39],"of":[40,47,54,80,102,122,156],"agents.":[41,124],"Hence,":[42],"enhancing":[43],"exploration":[45,120],"ability":[46,121],"improving":[50],"utilization":[52,100],"efficiency":[53,101],"are":[56,82],"two":[57],"critical":[58],"issues":[59],"learning.":[64],"We":[65],"propose":[66],"a":[67,113],"novel":[68],"method":[69],"called":[70],"Generative":[71],"Adversarial":[72],"Imitation":[73],"Learning":[74],"Policy":[75],"Gradients":[76],"(GAILPG).":[77],"The":[78],"contributions":[79],"GAILPG":[81,135],"as":[83],"follows:":[84],"(a)":[85],"we":[86,111],"integrate":[87],"generative":[88],"adversarial":[89],"self-imitation":[90],"learning":[91],"into":[92],"actor-critic":[95],"framework":[96],"improve":[98],"experiences,":[103],"thus":[104],"further":[105],"assisting":[106],"policy":[108],"training;":[109],"(b)":[110],"design":[112],"new":[114],"curiosity":[115,162],"module":[116,159,163],"enhance":[118],"Experimental":[125],"results":[126],"on":[127,143],"StarCraft":[129],"II":[130],"micromanagement":[131],"benchmark":[132],"demonstrate":[133],"that":[134],"surpasses":[136],"state-of-the-art":[137],"policy-based":[138],"methods":[139],"is":[141],"even":[142],"par":[144],"value-based":[147],"methods.":[148],"And":[149],"ablation":[151],"experiments":[152],"validate":[153],"reasonability":[155],"discriminator":[158],"encapsulated":[164],"our":[166],"method.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}