{"id":"https://openalex.org/W4324266596","doi":"https://doi.org/10.1145/3579654.3579702","title":"Trust Region Method Using K-FAC in Multi-Agent Reinforcement Learning","display_name":"Trust Region Method Using K-FAC in Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4324266596","doi":"https://doi.org/10.1145/3579654.3579702"},"language":"en","primary_location":{"id":"doi:10.1145/3579654.3579702","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579654.3579702","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579654.3579702","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3579654.3579702","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013115038","display_name":"Jiali Yu","orcid":"https://orcid.org/0000-0003-3815-3574"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiali Yu","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030271803","display_name":"Fengge Wu","orcid":"https://orcid.org/0000-0002-1958-8321"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengge Wu","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069584904","display_name":"Junsuo Zhao","orcid":"https://orcid.org/0000-0001-8950-4157"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsuo Zhao","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013115038"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16521043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9945999979972839,"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":0.8695456981658936},{"id":"https://openalex.org/keywords/kronecker-delta","display_name":"Kronecker delta","score":0.7267063856124878},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7265618443489075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7031208276748657},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.6636354923248291},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5479394197463989},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4862767457962036},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.48082029819488525},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43312567472457886},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34744155406951904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25495851039886475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1992332935333252}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8695456981658936},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.7267063856124878},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7265618443489075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031208276748657},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6636354923248291},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5479394197463989},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4862767457962036},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.48082029819488525},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43312567472457886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34744155406951904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25495851039886475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1992332935333252},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579654.3579702","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579654.3579702","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579654.3579702","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3579654.3579702","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579654.3579702","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579654.3579702","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4324266596.pdf","grobid_xml":"https://content.openalex.org/works/W4324266596.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2786036274","https://openalex.org/W2962747323","https://openalex.org/W2963433607","https://openalex.org/W2988070836","https://openalex.org/W3163926178"],"related_works":["https://openalex.org/W3153509215","https://openalex.org/W4301793409","https://openalex.org/W1986375199","https://openalex.org/W300594107","https://openalex.org/W1178061417","https://openalex.org/W2028667466","https://openalex.org/W2077314575","https://openalex.org/W2030956755","https://openalex.org/W2086054158","https://openalex.org/W1572165570"],"abstract_inverted_index":{"A":[0],"challenging":[1],"problem":[2],"in":[3,51,95],"multi-agent":[4,84],"reinforcement":[5],"learning":[6],"(MARL)":[7],"is":[8,17,90],"to":[9,29,36,114,136],"ensure":[10],"that":[11,103],"the":[12,26,38,45,83,96,115,128],"policy":[13,49],"converges":[14],"quickly":[15],"and":[16,59,120,132],"effective":[18],"with":[19,77,109],"limited":[20],"computing":[21,60,111],"resources.":[22],"This":[23],"paper":[24],"extends":[25],"second-order":[27],"optimization":[28],"MARL":[30,52],"using":[31,69],"Kronecker-factored":[32],"approximate":[33,37],"curvature":[34],"(K-FAC)":[35],"natural":[39],"gradient":[40],"update.":[41],"And":[42],"it":[43],"solves":[44],"challenge":[46],"of":[47,57,130],"training":[48],"networks":[50],"which":[53],"requires":[54],"a":[55,64],"lot":[56],"time":[58],"costs.":[61],"We":[62],"propose":[63],"Heterogeneous-agent":[65],"Trust":[66],"Region":[67],"algorithm":[68,89],"K-FAC":[70],"(HAKTR).":[71],"Further":[72],"more,":[73],"we":[74],"endow":[75],"HAKTR":[76,104,123],"monotonic":[78],"performance":[79],"improvement":[80],"based":[81],"on":[82,92],"advantage":[85],"decomposition":[86],"theorem.":[87],"Our":[88],"evaluated":[91],"continuous":[93],"tasks":[94],"MuJoCo":[97],"environment.":[98],"The":[99],"experimental":[100],"results":[101],"show":[102],"can":[105,133],"achieve":[106],"higher":[107],"rewards":[108],"less":[110],"costs":[112],"compared":[113],"baselines":[116],"such":[117],"as":[118],"HATRPO":[119],"HAPPO.":[121],"Moreover,":[122],"has":[124],"good":[125],"scalability":[126],"regarding":[127],"number":[129],"agents":[131],"be":[134],"applied":[135],"large-scale":[137],"networks.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}