{"id":"https://openalex.org/W4414432731","doi":"https://doi.org/10.1109/case58245.2025.11163856","title":"Group Confident Policy Optimization","display_name":"Group Confident Policy Optimization","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432731","doi":"https://doi.org/10.1109/case58245.2025.11163856"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5117668709","display_name":"Yao Li","orcid":"https://orcid.org/0000-0003-3752-6535"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Li","raw_affiliation_strings":["Tsinghua University,Department of Industrial Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Industrial Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075946797","display_name":"Zhenglin Liang","orcid":"https://orcid.org/0000-0003-2572-9423"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenglin Liang","raw_affiliation_strings":["Tsinghua University,Department of Industrial Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Industrial Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"995","last_page":"1000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.7106000185012817,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10734","display_name":"Information and Cyber Security","score":0.7106000185012817,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10927","display_name":"Access Control and Trust","score":0.6114000082015991,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6635000109672546},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.6335999965667725},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.49380001425743103},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4214000105857849},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4097999930381775},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4050000011920929},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.36410000920295715},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.35589998960494995}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6635000109672546},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.6335999965667725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5710999965667725},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2777632292","wikidata":"https://www.wikidata.org/wiki/Q315515","display_name":"Discretion","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2116942894","https://openalex.org/W3150718622","https://openalex.org/W3214464180","https://openalex.org/W4213435521","https://openalex.org/W4312803983","https://openalex.org/W4321611535","https://openalex.org/W4367663227","https://openalex.org/W4386432124","https://openalex.org/W4388692115","https://openalex.org/W4389065366","https://openalex.org/W4389417302","https://openalex.org/W4390939851","https://openalex.org/W4391092742","https://openalex.org/W4391667216","https://openalex.org/W4398151096","https://openalex.org/W4403936322","https://openalex.org/W4405846500"],"related_works":[],"abstract_inverted_index":{"Learning-based":[0],"policy":[1,59,89],"improvement":[2,101],"methods":[3],"rely":[4],"on":[5],"extensive":[6],"data":[7,79],"collection":[8],"and":[9,28,53,58,80,98],"iterative":[10],"training,":[11],"leading":[12],"to":[13,25,72,118,137],"credibility":[14],"challenges":[15],"during":[16],"early":[17],"training":[18,74,104],"stage":[19],"when":[20],"the":[21,51,103,119,124,128],"agent":[22,96],"is":[23],"transferred":[24],"new,":[26],"uncertain":[27],"risky":[29,115],"environments.":[30],"To":[31],"address":[32],"this,":[33],"this":[34,92],"paper":[35],"develops":[36],"a":[37,64,82],"novel":[38],"reinforcement":[39],"learning":[40],"algorithm,":[41],"termed":[42],"Group":[43],"Confident":[44],"Policy":[45],"Optimization":[46],"(GCPO),":[47],"which":[48],"emphasizes":[49],"enhancing":[50],"safety":[52],"confidence":[54],"of":[55,130],"exploration":[56],"processes":[57],"updates.":[60],"The":[61],"algorithm":[62],"proposes":[63],"confident":[65,131],"advantage":[66,132],"function":[67],"that":[68,109],"leverages":[69],"group":[70],"normalization":[71],"mitigate":[73],"variance":[75],"induced":[76],"by":[77],"sampled":[78],"introduces":[81],"confidence-based":[83],"corrective":[84],"factor.":[85],"By":[86],"employing":[87],"confidence-augmented":[88],"gradient":[90],"updates,":[91],"method":[93],"ensures":[94],"safe":[95],"behaviors":[97],"progressive":[99],"performance":[100,113],"throughout":[102],"cycle.":[105],"Simulation":[106],"experiments":[107],"demonstrate":[108],"GCPO":[110],"achieves":[111],"superior":[112],"in":[114,145],"tasks":[116],"compared":[117],"traditional":[120],"PPO":[121],"method,":[122],"while":[123],"ablation":[125],"study":[126],"verifies":[127],"importance":[129],"estimation.":[133],"These":[134],"findings":[135],"contribute":[136],"establishing":[138],"trustworthy":[139],"engineering":[140],"paradigms":[141],"for":[142],"safety-critical":[143],"automation":[144],"cross-environment":[146],"transfer":[147],"scenarios.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}