{"id":"https://openalex.org/W4312266960","doi":"https://doi.org/10.1109/icpr56361.2022.9956417","title":"Data-Efficient Deep Reinforcement Learning with Symmetric Consistency","display_name":"Data-Efficient Deep Reinforcement Learning with Symmetric Consistency","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312266960","doi":"https://doi.org/10.1109/icpr56361.2022.9956417"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956417","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5006269113","display_name":"Xianchao Zhang","orcid":"https://orcid.org/0000-0002-0180-3740"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianchao Zhang","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China","School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072809063","display_name":"Wentao Yang","orcid":"https://orcid.org/0000-0002-8306-5840"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Yang","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China","School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403816","display_name":"Xiaotong Zhang","orcid":"https://orcid.org/0000-0002-5013-8476"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotong Zhang","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China","School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349058","display_name":"Han Liu","orcid":"https://orcid.org/0000-0003-0647-6627"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China","School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076222551","display_name":"Guanglu Wang","orcid":"https://orcid.org/0000-0002-9968-3547"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglu Wang","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China","School of Software Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"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":"119","issue":null,"first_page":"2430","last_page":"2436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9746999740600586,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9593999981880188,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7872409820556641},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6843470335006714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6590105295181274},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6243888139724731},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5848798155784607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49592623114585876},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33396804332733154},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24272394180297852}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7872409820556641},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6843470335006714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6590105295181274},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6243888139724731},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5848798155784607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49592623114585876},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33396804332733154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24272394180297852},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956417","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2097356275","https://openalex.org/W2141125852","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2156163116","https://openalex.org/W2163605009","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2781585732","https://openalex.org/W2904246096","https://openalex.org/W2920362155","https://openalex.org/W2951799221","https://openalex.org/W2952867909","https://openalex.org/W2964043796","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W3005173720","https://openalex.org/W3015437096","https://openalex.org/W3021708257","https://openalex.org/W3035524453","https://openalex.org/W3115293622","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W6674360390","https://openalex.org/W6684191040","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6747387971","https://openalex.org/W6757592117","https://openalex.org/W6760405395","https://openalex.org/W6772005887","https://openalex.org/W6773738434","https://openalex.org/W6776867236","https://openalex.org/W6780470247","https://openalex.org/W6787713516"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2051487156","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Data":[0],"augmentation":[1],"methods":[2,178],"have":[3,103],"proven":[4],"highly":[5],"effective":[6],"in":[7,26,35,57],"supervised":[8],"learning":[9,29,177],"domains":[10],"where":[11],"semantic-invariant":[12],"perturbations":[13],"can":[14],"be":[15],"easily":[16],"applied":[17],"to":[18,40,66,94],"the":[19,32,36,54,63,90,96,111,123,126,132,142,151,173],"labeled":[20],"input":[21],"examples.":[22],"However,":[23],"some":[24],"used":[25],"deep":[27,175],"reinforcement":[28,176],"cannot":[30],"guarantee":[31],"consistent":[33,83],"semantics":[34],"transition":[37],"samples,":[38],"leading":[39],"wrong":[41],"value":[42,133],"estimation":[43,134],"and":[44,59,61,72,86,107,117,125,163],"optimization":[45],"during":[46],"training.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,80],"focus":[52],"on":[53,75,89,150],"symmetric":[55,98,101,127],"consistency":[56],"states":[58,116],"actions,":[60],"propose":[62],"Symmetric":[64,129,145,155],"DQN":[65,130,146,156],"maintain":[67],"it":[68],"for":[69],"better":[70],"performance":[71],"data":[73,77,180],"efficiency":[74],"small":[76],"regimes.":[78],"Specifically,":[79],"adopt":[81],"a":[82,158,164],"state":[84],"flip":[85],"action":[87],"projection":[88],"original":[91,112,124],"interaction":[92],"transitions":[93],"construct":[95],"corresponding":[97],"ones.":[99],"The":[100],"ones":[102,113],"similar":[104],"middle":[105],"rewards":[106],"terminal":[108],"signals":[109],"as":[110],"but":[114],"reverse":[115],"actions.":[118],"Therefore,":[119],"by":[120,147],"optimizing":[121],"both":[122],"losses,":[128],"facilitates":[131],"from":[135],"two":[136],"directions":[137],"per":[138],"transition.":[139],"We":[140],"illustrate":[141],"promise":[143],"of":[144,161,167,172],"conducting":[148],"experiments":[149],"Atari":[152],"100K":[153],"benchmark.":[154],"achieves":[157],"median":[159],"HNS":[160,166],"27.6%":[162],"mean":[165],"51.1%,":[168],"which":[169],"surpasses":[170],"most":[171],"previous":[174],"with":[179],"augmentation.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}