{"id":"https://openalex.org/W4214565169","doi":"https://doi.org/10.1145/3488933.3489029","title":"Meta Actor-Critic Framework for Multi-Agent Reinforcement Learning","display_name":"Meta Actor-Critic Framework for Multi-Agent Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-24","ids":{"openalex":"https://openalex.org/W4214565169","doi":"https://doi.org/10.1145/3488933.3489029"},"language":"en","primary_location":{"id":"doi:10.1145/3488933.3489029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488933.3489029","pdf_url":null,"source":{"id":"https://openalex.org/S4363608564","display_name":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","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/A5043962660","display_name":"Jiateng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiateng Huang","raw_affiliation_strings":["Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020177243","display_name":"Wanrong Huang","orcid":"https://orcid.org/0000-0001-5778-9055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanrong Huang","raw_affiliation_strings":["Artifcial Intelligence Research Center, National Innovation Institute of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Artifcial Intelligence Research Center, National Innovation Institute of Defense Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061911091","display_name":"Dan Wu","orcid":"https://orcid.org/0000-0002-3856-1087"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Wu","raw_affiliation_strings":["College of Computer & Hefei Interdisciplinary Center, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Computer & Hefei Interdisciplinary Center, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060251766","display_name":"Long Lan","orcid":"https://orcid.org/0000-0002-4238-8985"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lan","raw_affiliation_strings":["Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information & State Key Laboratory of High Performance Computing, College of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043962660"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23452982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9797000288963318,"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":0.9553999900817871,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8484296798706055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497124671936035},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5719174146652222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500940680503845},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5097638964653015},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09433501958847046}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8484296798706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497124671936035},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5719174146652222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500940680503845},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5097638964653015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09433501958847046},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3488933.3489029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488933.3489029","pdf_url":null,"source":{"id":"https://openalex.org/S4363608564","display_name":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 4th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2000514530","https://openalex.org/W2173248099","https://openalex.org/W2602275733","https://openalex.org/W2604763608","https://openalex.org/W2623431351","https://openalex.org/W2747329762","https://openalex.org/W2762872434","https://openalex.org/W2787938642","https://openalex.org/W2794643322","https://openalex.org/W2912757816","https://openalex.org/W2963900541","https://openalex.org/W2979869797","https://openalex.org/W2996894943","https://openalex.org/W3091905527","https://openalex.org/W6765978294","https://openalex.org/W6767015469","https://openalex.org/W6771843596"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3130669838","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"In":[0,31,130],"recent":[1],"years,":[2],"multi-agent":[3,59,128,141],"reinforcement":[4],"learning":[5,46,60,83],"has":[6],"received":[7],"sustained":[8],"attention":[9],"in":[10,112],"the":[11,28,49,74,80,88,92,96,99,107,119,132],"last":[12],"few":[13],"years.":[14],"The":[15],"typical":[16],"Actor-Critic":[17,142],"methods":[18],"learn":[19],"mappings":[20],"directly":[21],"from":[22],"observation":[23],"to":[24,55,72,78,102],"action":[25],"without":[26],"understanding":[27],"tasks":[29],"themselves.":[30],"this":[32],"paper,":[33],"we":[34],"present":[35],"a":[36],"meta":[37,93],"actor-critic":[38],"framework":[39,115,123,133],"for":[40],"meta-actor":[41],"critique":[42],"based":[43],"on":[44,124],"observational":[45],"processes":[47],"and":[48,57,109,116],"additional":[50],"loss":[51,77,89],"of":[52,90,98,121,127],"meta-learning":[53],"actors":[54],"accelerate":[56],"improve":[58],"across":[61],"agents'":[62],"experiences.":[63],"Within":[64],"our":[65,113,122],"framework,":[66],"all":[67],"agents":[68],"are":[69],"deliberately":[70],"designed":[71],"share":[73],"same":[75],"meta-critic":[76],"achieve":[79],"optimum":[81],"actor":[82,94],"progress.":[84],"Meanwhile,":[85],"by":[86],"minimizing":[87],"meta-actors,":[91],"learns":[95],"features":[97],"meta-observation,":[100],"leading":[101],"better":[103],"actions.":[104],"We":[105],"implemented":[106],"MADDPG":[108],"MATD3":[110],"algorithms":[111],"proposed":[114],"empirically":[117],"demonstrated":[118],"superiority":[120],"two":[125],"kinds":[126],"tasks.":[129],"addition,":[131],"can":[134],"be":[135],"flexibly":[136],"incorporated":[137],"into":[138],"various":[139],"contemporary":[140],"methods.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}