{"id":"https://openalex.org/W3111843786","doi":"https://doi.org/10.1109/smc42975.2020.9283339","title":"AHAC: Actor Hierarchical Attention Critic for Multi-Agent Reinforcement Learning","display_name":"AHAC: Actor Hierarchical Attention Critic for Multi-Agent Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3111843786","doi":"https://doi.org/10.1109/smc42975.2020.9283339","mag":"3111843786"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9283339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100455413","display_name":"Yajie Wang","orcid":"https://orcid.org/0000-0002-0962-4464"},"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":"Yajie Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"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":"Dianxi Shi","raw_affiliation_strings":["National Innovation Institute of Defense Technology, Beijing, China","Tianjin Artificial Intelligence Innovation Center, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"National Innovation Institute of Defense Technology, Beijing, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100884245","display_name":"Chao Xue","orcid":"https://orcid.org/0000-0002-9507-9991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Xue","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763478","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-8304-3692"},"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":"Hao Jiang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031404939","display_name":"Gongju Wang","orcid":"https://orcid.org/0000-0002-7162-3067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gongju Wang","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026199735","display_name":"Peng Gong","orcid":"https://orcid.org/0000-0001-6352-1696"},"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":"Peng Gong","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100455413"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69908182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3013","last_page":"3020"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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":0.9908000230789185,"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":0.8227697610855103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6952461004257202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44168901443481445},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3617478013038635}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8227697610855103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952461004257202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44168901443481445},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3617478013038635}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc42975.2020.9283339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W56117469","https://openalex.org/W206679605","https://openalex.org/W1484210532","https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W2099618002","https://openalex.org/W2133564696","https://openalex.org/W2145339207","https://openalex.org/W2147527908","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2418628973","https://openalex.org/W2470673105","https://openalex.org/W2547875792","https://openalex.org/W2592798481","https://openalex.org/W2597655663","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2781726626","https://openalex.org/W2803155336","https://openalex.org/W2894976951","https://openalex.org/W2950527759","https://openalex.org/W2950560044","https://openalex.org/W2951527505","https://openalex.org/W2962938168","https://openalex.org/W2962966033","https://openalex.org/W2963403868","https://openalex.org/W2963407617","https://openalex.org/W2963658727","https://openalex.org/W2963717208","https://openalex.org/W2963864421","https://openalex.org/W2963881016","https://openalex.org/W2964308564","https://openalex.org/W2998367975","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W4303633609","https://openalex.org/W4385245566","https://openalex.org/W6602332174","https://openalex.org/W6628927728","https://openalex.org/W6637033378","https://openalex.org/W6679434410","https://openalex.org/W6682137061","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684821475","https://openalex.org/W6684921986","https://openalex.org/W6717018068","https://openalex.org/W6729448088","https://openalex.org/W6734678876","https://openalex.org/W6735377749","https://openalex.org/W6735650757","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6747473740","https://openalex.org/W6751139674","https://openalex.org/W6755069753","https://openalex.org/W6770126465"],"related_works":["https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4319773215","https://openalex.org/W4224287422","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3005560120","https://openalex.org/W3037422413","https://openalex.org/W2959276766"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,84,165],"has":[3],"made":[4],"significant":[5],"progress":[6],"in":[7,10,28,166,200,204],"multi-agent":[8],"tasks":[9],"recent":[11],"years.":[12],"However,":[13],"most":[14],"previous":[15],"studies":[16],"focus":[17],"on":[18],"solving":[19],"full":[20],"cooperative":[21,195],"tasks,":[22,33],"which":[23],"do":[24],"not":[25,191],"perform":[26],"well":[27],"mixed":[29,32,71,167,201],"tasks.":[30,72,168],"In":[31,169],"the":[34,40,57,95,114,135,138,205],"agent":[35],"needs":[36],"to":[37,47,56,65,107,122,140,144,194],"comprehensively":[38],"consider":[39],"information":[41,68,82,116,145,181],"provided":[42],"by":[43],"friends":[44,147],"and":[45,51,100,119,137,148,151,163],"enemies":[46,149],"learn":[48,67],"its":[49,52],"strategy,":[50],"strategy":[53],"is":[54,61,190],"sensitive":[55],"received":[58,115],"information.":[59],"There":[60],"a":[62],"great":[63],"necessity":[64],"efficiently":[66],"representation":[69,83],"for":[70,85],"To":[73],"this":[74],"end,":[75],"we":[76],"present":[77],"an":[78],"approach":[79,93,172,189,209],"that":[80,177,187],"conducts":[81],"multiple":[86],"agents":[87],"using":[88],"hierarchical":[89,105,127],"attention":[90,106,128,133],"mechanism.":[91],"Our":[92],"adopts":[94],"framework":[96],"of":[97,146],"centralized":[98],"training":[99],"decentralized":[101],"execution.":[102],"It":[103,158],"applies":[104],"centrally":[108],"computed":[109],"critics,":[110],"so":[111],"critics":[112],"process":[113,178],"more":[117,161,182],"accurately":[118],"assist":[120],"actors":[121],"choose":[123],"better":[124,199],"actions.":[125],"The":[126],"critic":[129],"uses":[130,173],"two":[131],"different":[132,142],"levels,":[134],"agent-level":[136],"group-level,":[139],"assign":[141],"weights":[143],"respectively":[150],"then":[152],"summarize":[153],"them":[154],"at":[155],"each":[156],"time-step.":[157],"can":[159],"achieve":[160],"effective":[162],"scalable":[164],"addition,":[170],"our":[171,188,208],"recurrent":[174],"neural":[175],"networks":[176],"sequence":[179],"input":[180],"efficiently.":[183],"Experimental":[184],"results":[185],"show":[186],"only":[192],"applicable":[193],"environments":[196],"but":[197],"also":[198],"environments.":[202],"Especially":[203],"predator-prey":[206],"task,":[207],"receives":[210],"twice":[211],"as":[212,215],"much":[213],"reward":[214],"baselines.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}