{"id":"https://openalex.org/W4386547607","doi":"https://doi.org/10.3233/jifs-233747","title":"An efficient and robust gradient reinforcement learning: Deep comparative policy","display_name":"An efficient and robust gradient reinforcement learning: Deep comparative policy","publication_year":2023,"publication_date":"2023-09-08","ids":{"openalex":"https://openalex.org/W4386547607","doi":"https://doi.org/10.3233/jifs-233747"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-233747","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-233747","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-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/A5071336373","display_name":"Jia\u2010Guo Wang","orcid":"https://orcid.org/0009-0002-4982-4839"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaguo Wang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033908707","display_name":"Wenheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133467","display_name":"Xi'an Aeronautical University","ror":"https://ror.org/03qn8zy63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210133467"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenheng Li","raw_affiliation_strings":["AVIC Xi\u2019an Aeronautics Computing Technique Research Institute, Xi\u2019an, China","AVIC Xi'an Aeronautics Computing Technique Research Institute, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"AVIC Xi\u2019an Aeronautics Computing Technique Research Institute, Xi\u2019an, China","institution_ids":["https://openalex.org/I4210133467"]},{"raw_affiliation_string":"AVIC Xi'an Aeronautics Computing Technique Research Institute, Xi'an, China","institution_ids":["https://openalex.org/I4210133467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034157762","display_name":"Chao Lei","orcid":"https://orcid.org/0000-0001-7404-758X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chao Lei","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Parkville, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Parkville, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083408391","display_name":"Meng Yang","orcid":"https://orcid.org/0000-0001-5630-6357"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Clayton Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Clayton Victoria, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070791321","display_name":"Yang Pei","orcid":"https://orcid.org/0000-0002-7907-9019"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Pei","raw_affiliation_strings":["Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070791321"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55733981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"46","issue":"2","first_page":"3773","last_page":"3788"},"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":0.9929999709129333,"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":0.9901000261306763,"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/initialization","display_name":"Initialization","score":0.7374457120895386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925582885742188},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6555892825126648},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6443754434585571},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5725778341293335},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5484649538993835},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4739651381969452},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43092596530914307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42884156107902527},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42835015058517456},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.4107969105243683},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19885212182998657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1920168101787567},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08007577061653137}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7374457120895386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925582885742188},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6555892825126648},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6443754434585571},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5725778341293335},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5484649538993835},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4739651381969452},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43092596530914307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42884156107902527},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42835015058517456},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.4107969105243683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19885212182998657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1920168101787567},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08007577061653137},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-233747","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-233747","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1979071892","https://openalex.org/W1994710951","https://openalex.org/W2107726111","https://openalex.org/W2165501837","https://openalex.org/W2257979135","https://openalex.org/W2546938941","https://openalex.org/W2562491047","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W6729383884","https://openalex.org/W6744838376"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W3095877357","https://openalex.org/W183202219","https://openalex.org/W10861731","https://openalex.org/W2072565696","https://openalex.org/W2050451745"],"abstract_inverted_index":{"Recently,":[0],"actor-critic":[1],"architectures":[2],"such":[3],"as":[4],"deep":[5,169],"deterministic":[6],"policy":[7,171],"gradient":[8,80,141],"(DDPG)":[9],"are":[10,98,203],"able":[11],"to":[12,67,82,103,110,114,145,168,220,234],"understand":[13],"higher-level":[14],"concepts":[15],"for":[16,125,274],"searching":[17],"rich":[18],"reward,":[19],"and":[20,28,40,50,58,101,200,205,218,251,254,288],"generate":[21],"complex":[22,272],"actions":[23],"in":[24,31,132,155,162,207,247,258,264],"continuous":[25],"action":[26,36,76,86,239,266],"space,":[27],"widely":[29],"used":[30],"practical":[32],"applications.":[33],"However,":[34],"when":[35],"space":[37,77,87,240],"is":[38,65,108,150,184,215,231,270,278],"limited":[39],"has":[41],"dynamic":[42,100,261],"hard":[43,96,262],"margins,":[44,241],"training":[45,129,180,249],"DDPG":[46,105,167,225],"can":[47,226,243,284],"be":[48,68,131,235,286],"problematic":[49],"inefficiency.":[51],"Since":[52],"real-world":[53],"actuators":[54,89],"always":[55,285],"have":[56],"margins":[57,97,263],"interferences,":[59],"after":[60],"initialization,":[61],"the":[62,83,92,95,104,122,128,147,178,238,265,281],"actor":[63,79,148],"network":[64,144,149],"likely":[66,233],"stuck":[69],"at":[70,91],"a":[71,152,187],"local":[72,117,126,252],"optimal":[73],"point":[74],"on":[75,140],"margin:":[78],"orients":[81],"outside":[84],"of":[85,135,142,182,197],"but":[88],"stop":[90],"margin.":[93],"If":[94,119],"complex,":[99],"unknown":[102],"agent,":[106],"it":[107],"unable":[109],"use":[111],"penalty":[112,273],"functions":[113],"recover":[115],"from":[116],"optimum.":[118],"we":[120,165],"enlarge":[121],"random":[123,191],"process":[124,181],"exploration,":[127],"could":[130],"potential":[133],"risk":[134],"failure.":[136],"Therefore,":[137],"simply":[138],"relying":[139],"critic":[143],"train":[146],"not":[151,279],"robust":[153],"method":[154],"real":[156],"environment.":[157],"To":[158],"solve":[159],"this":[160,163],"problem,":[161],"paper":[164],"modify":[166],"comparative":[170],"(DCP).":[172],"Rather":[173],"than":[174],"leveraging":[175],"critic-to-actor":[176],"gradient,":[177],"core":[179],"DCP":[183,199,214,230,242],"regulated":[185],"by":[186,237],"T-fold":[188],"compare":[189],"among":[190],"proposed":[192],"adjacent":[193],"actions.":[194],"The":[195],"performance":[196],"DDPG,":[198],"related":[201],"algorithms":[202],"tested":[204],"compared":[206],"two":[208],"experiments.":[209],"Our":[210],"results":[211],"show":[212],"that,":[213,271],"effective,":[216],"efficient":[217],"qualified":[219],"perform":[221],"all":[222],"tasks":[223],"that":[224],"perform.":[227],"More":[228],"importantly,":[229],"less":[232],"influenced":[236],"provide":[244],"more":[245,256],"safety":[246],"avoiding":[248],"failure":[250],"optimum,":[253],"gain":[255],"robustness":[257],"applications":[259],"with":[260],"space.":[267],"Another":[268],"advantage":[269],"margin":[275],"touching":[276],"detection":[277],"required,":[280],"reward":[282],"function":[283],"brief":[287],"short.":[289]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}