{"id":"https://openalex.org/W4286901586","doi":"https://doi.org/10.3389/fnbot.2022.1081242","title":"Realistic Actor-Critic: A framework for balance between value overestimation and underestimation","display_name":"Realistic Actor-Critic: A framework for balance between value overestimation and underestimation","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4286901586","doi":"https://doi.org/10.3389/fnbot.2022.1081242","pmid":"https://pubmed.ncbi.nlm.nih.gov/36699950"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2022.1081242","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1081242","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1081242/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1081242/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058925032","display_name":"Sicen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicen Li","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037803929","display_name":"Qinyun Tang","orcid":"https://orcid.org/0000-0001-7687-0166"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyun Tang","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106426681","display_name":"Yiming Pang","orcid":"https://orcid.org/0000-0003-1307-2700"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Pang","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031747363","display_name":"Xinmeng Ma","orcid":"https://orcid.org/0000-0002-5079-4481"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinmeng Ma","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367342","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-0741-9838"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Wang","raw_affiliation_strings":["College of Shipbuilding Engineering, Harbin Engineering University, Harbin, China","Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Shipbuilding Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Science and Technology on Underwater Vehicle Laboratory, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100367342"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":1.011,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79844199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":null,"first_page":"1081242","last_page":"1081242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2632000148296356,"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":0.2632000148296356,"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":0.24210000038146973,"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":0.0957999974489212,"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/computer-science","display_name":"Computer science","score":0.8247476816177368},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7293832898139954},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.691099226474762},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5882664918899536},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.5674076676368713},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47754204273223877},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.428333580493927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37738895416259766},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3713679313659668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36620253324508667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0985422432422638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8247476816177368},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7293832898139954},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.691099226474762},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5882664918899536},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.5674076676368713},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47754204273223877},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.428333580493927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37738895416259766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3713679313659668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36620253324508667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0985422432422638},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2022.1081242","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1081242","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1081242/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:36699950","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36699950","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9868235","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9868235","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9868235/pdf/fnbot-16-1081242.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:2743889fedbe47bca936a76a79fb7e2b","is_oa":true,"landing_page_url":"https://doaj.org/article/2743889fedbe47bca936a76a79fb7e2b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 16 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2022.1081242","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1081242","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1081242/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1949792850","display_name":null,"funder_award_id":"YQ2020E028","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"},{"id":"https://openalex.org/G7438603167","display_name":null,"funder_award_id":"51779059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4286901586.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1505937442","https://openalex.org/W2145014875","https://openalex.org/W2158782408","https://openalex.org/W2767313115","https://openalex.org/W2904246096","https://openalex.org/W2914362802","https://openalex.org/W2952348496","https://openalex.org/W2954360742","https://openalex.org/W2962736495","https://openalex.org/W2964121744","https://openalex.org/W2991274265","https://openalex.org/W3000146453","https://openalex.org/W3004082694","https://openalex.org/W3005861412","https://openalex.org/W3006670279","https://openalex.org/W3008003828","https://openalex.org/W3012148463","https://openalex.org/W3021619395","https://openalex.org/W3090820436","https://openalex.org/W3098341014","https://openalex.org/W3102100346","https://openalex.org/W3105706360","https://openalex.org/W3123454130","https://openalex.org/W3124816456","https://openalex.org/W3162450516","https://openalex.org/W3164731060","https://openalex.org/W3166411989","https://openalex.org/W3201326803","https://openalex.org/W4225283319","https://openalex.org/W4287322058","https://openalex.org/W4287330094","https://openalex.org/W4287824211","https://openalex.org/W4287867830","https://openalex.org/W4298412418","https://openalex.org/W4394666657","https://openalex.org/W6602057636","https://openalex.org/W6776730770"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W3183136280","https://openalex.org/W2775233965","https://openalex.org/W3114716045","https://openalex.org/W4281847915"],"abstract_inverted_index":{"Introduction:":[0],"The":[1],"value":[2,48,71,94,124,248],"approximation":[3],"bias":[4,15,49,72],"is":[5,159],"known":[6],"to":[7,9,34,65,79,92,118,149,205,243,266],"lead":[8],"suboptimal":[10],"policies":[11,121,241],"or":[12],"catastrophic":[13],"overestimation":[14,97,136,181],"accumulation":[16],"that":[17,142,194,258],"prevent":[18],"the":[19,23,36,47,67,70,75,127,154,164,175,183,209,215,233,238,271],"agent":[20],"from":[21],"making":[22],"right":[24],"decisions":[25],"between":[26],"exploration":[27,57,171],"and":[28,52,73,96,200],"exploitation.":[29],"Algorithms":[30],"have":[31],"been":[32],"proposed":[33],"mitigate":[35],"above":[37],"contradiction.":[38],"However,":[39],"we":[40],"still":[41,179],"lack":[42],"an":[43],"understanding":[44],"of":[45,69,163,240],"how":[46],"impact":[50],"performance":[51,202],"a":[53,87,104,133,160,254],"method":[54],"for":[55,230],"efficient":[56],"while":[58,178],"keeping":[59],"stable":[60],"updates.":[61],"This":[62,84,101,139,223],"study":[63,85,102,140,191],"aims":[64],"clarify":[66],"effect":[68],"improve":[74,267],"reinforcement":[76],"learning":[77],"algorithms":[78],"enhance":[80],"sample":[81,198,268],"efficiency.":[82],"Methods:":[83],"designs":[86],"simple":[88],"episodic":[89],"tabular":[90],"MDP":[91],"research":[93,224,231],"underestimation":[95],"in":[98,153,208,270],"actor-critic":[99,264],"methods.":[100],"proposes":[103,253],"unified":[105,256],"framework":[106,257],"called":[107],"Realistic":[108],"Actor-Critic":[109,207],"(RAC),":[110],"which":[111,158],"employs":[112],"Universal":[113],"Value":[114],"Function":[115],"Approximators":[116],"(UVFA)":[117],"simultaneously":[119],"learn":[120],"with":[122,126,132,262],"different":[123,134,247],"confidence-bound":[125],"same":[128],"neural":[129],"network,":[130],"each":[131],"under":[135,246],"trade-off.":[137],"Results:":[138],"highlights":[141],"agents":[143],"could":[144],"over-explore":[145],"low-value":[146,244],"states":[147,245],"due":[148],"inflexible":[150],"under-overestimation":[151],"trade-off":[152,235],"fixed":[155],"hyperparameters":[156],"setting,":[157],"particular":[161],"form":[162],"exploration-exploitation":[165,234],"dilemma.":[166],"And":[167],"RAC":[168,195],"performs":[169],"directed":[170],"without":[172],"over-exploration":[173],"using":[174,182],"upper":[176],"bounds":[177],"avoiding":[180],"lower":[184],"bounds.":[185],"Through":[186],"carefully":[187],"designed":[188],"experiments,":[189],"this":[190],"empirically":[192],"verifies":[193],"achieves":[196],"10x":[197],"efficiency":[199,269],"25%":[201],"improvement":[203],"compared":[204],"Soft":[206],"most":[210],"challenging":[211],"Humanoid":[212],"environment.":[213],"All":[214],"source":[216],"codes":[217],"are":[218],"available":[219],"at":[220],"https://github.com/ihuhuhu/RAC.":[221],"Discussion:":[222],"not":[225],"only":[226],"provides":[227],"valuable":[228],"insights":[229],"on":[232],"by":[236],"studying":[237],"frequency":[239],"access":[242],"confidence-bounds":[249],"guidance,":[250],"but":[251],"also":[252],"new":[255],"can":[259],"be":[260],"combined":[261],"current":[263],"methods":[265],"continuous":[272],"control":[273],"domain.":[274]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}