{"id":"https://openalex.org/W4283448950","doi":"https://doi.org/10.1109/cog51982.2022.9893666","title":"CGAR: Critic Guided Action Redistribution in Reinforcement Leaning","display_name":"CGAR: Critic Guided Action Redistribution in Reinforcement Leaning","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4283448950","doi":"https://doi.org/10.1109/cog51982.2022.9893666"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","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/A5073678073","display_name":"Tairan Huang","orcid":"https://orcid.org/0000-0001-6672-7315"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tairan Huang","raw_affiliation_strings":["SCSE Beihang University,Beijing,China","SCSE Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SCSE Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"SCSE Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342434","display_name":"Xu Li","orcid":"https://orcid.org/0000-0002-0345-7677"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Cognitive Computing Lab Baidu Research,Beijing,China","Cognitive Computing Lab Baidu Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research,Beijing,China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348617","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-6294-6761"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["ECE Peking University,Beijing,China","ECE Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ECE Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ECE Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101074936","display_name":"Mingming Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]},{"id":"https://openalex.org/I4210159958","display_name":"Cognitive Research (United States)","ror":"https://ror.org/04s361q55","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159958"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Mingming Sun","raw_affiliation_strings":["Cognitive Computing Lab Baidu Research,Seattle,USA","Cognitive Computing Lab Baidu Research, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research,Seattle,USA","institution_ids":["https://openalex.org/I4210159958","https://openalex.org/I98301712"]},{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research, Seattle, USA","institution_ids":["https://openalex.org/I4210159958","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435506","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-3314-943X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]},{"id":"https://openalex.org/I4210159958","display_name":"Cognitive Research (United States)","ror":"https://ror.org/04s361q55","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159958"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Cognitive Computing Lab Baidu Research,Seattle,USA","Cognitive Computing Lab Baidu Research, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research,Seattle,USA","institution_ids":["https://openalex.org/I4210159958","https://openalex.org/I98301712"]},{"raw_affiliation_string":"Cognitive Computing Lab Baidu Research, Seattle, USA","institution_ids":["https://openalex.org/I4210159958","https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073678073"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05590344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1801 690","issue":null,"first_page":"496","last_page":"499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9739000201225281,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9628000259399414,"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":0.894270658493042},{"id":"https://openalex.org/keywords/redistribution","display_name":"Redistribution (election)","score":0.757443904876709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6695794463157654},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5139707922935486},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5035316348075867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4524950683116913},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44802531599998474},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4368993639945984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1958208978176117},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13916999101638794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.894270658493042},{"id":"https://openalex.org/C74080474","wikidata":"https://www.wikidata.org/wiki/Q7305975","display_name":"Redistribution (election)","level":3,"score":0.757443904876709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6695794463157654},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5139707922935486},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5035316348075867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4524950683116913},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44802531599998474},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4368993639945984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1958208978176117},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13916999101638794},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog51982.2022.9893666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1821462560","https://openalex.org/W2098774185","https://openalex.org/W2145339207","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2949561945","https://openalex.org/W2963864421","https://openalex.org/W2997006708","https://openalex.org/W3004127093","https://openalex.org/W3044994704","https://openalex.org/W3107951310","https://openalex.org/W3131143179","https://openalex.org/W4205923765","https://openalex.org/W4206145040","https://openalex.org/W4206318069","https://openalex.org/W6638523607","https://openalex.org/W6674884181","https://openalex.org/W6677916085","https://openalex.org/W6684921986","https://openalex.org/W6734517396","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6781244629","https://openalex.org/W6785535465","https://openalex.org/W6791138463"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W3005557527"],"abstract_inverted_index":{"Training":[0],"a":[1,17,71],"game-playing":[2],"reinforcement":[3],"learning":[4],"agent":[5],"requires":[6],"multiple":[7],"interactions":[8],"with":[9],"the":[10,35,38,46,60,63,68,76,81,86,91,103,115],"environment.":[11],"Ignorant":[12],"random":[13],"exploration":[14],"may":[15],"cause":[16],"waste":[18],"of":[19,37],"time":[20],"and":[21,99,118],"resources.":[22],"It's":[23],"essential":[24],"to":[25,59,74],"alleviate":[26],"such":[27],"waste.":[28],"As":[29],"discussed":[30],"in":[31],"this":[32],"paper,":[33],"under":[34],"settings":[36],"off-policy":[39],"actor":[40],"critic":[41,47,69],"algorithms,":[42],"we":[43],"demonstrate":[44,110],"that":[45,111],"can":[48,124],"bring":[49],"more":[50],"expected":[51],"discounted":[52],"rewards":[53],"than":[54],"or":[55],"at":[56,127],"least":[57],"equal":[58],"actor.":[61,87],"Thus,":[62],"Q":[64],"value":[65],"predicted":[66,84],"by":[67,85],"is":[70],"better":[72],"signal":[73],"redistribute":[75],"action":[77],"originally":[78],"sampled":[79],"from":[80],"policy":[82],"distribution":[83],"This":[88],"paper":[89],"introduces":[90],"novel":[92],"Critic":[93],"Guided":[94],"Action":[95],"Redistribution":[96],"(CGAR)":[97],"algorithm":[98],"tests":[100],"it":[101],"on":[102],"OpenAI":[104],"MuJoCo":[105],"tasks.":[106],"The":[107],"experimental":[108],"results":[109],"our":[112],"method":[113],"improves":[114],"sample":[116],"efficiency":[117],"achieves":[119],"state-of-the-art":[120],"performance.":[121],"Our":[122],"code":[123],"be":[125],"found":[126],"https://github.com/tairanhuang/CGAR.":[128]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}