{"id":"https://openalex.org/W4387303358","doi":"https://doi.org/10.1109/tnnls.2023.3317628","title":"Sampling Efficient Deep Reinforcement Learning Through Preference-Guided Stochastic Exploration","display_name":"Sampling Efficient Deep Reinforcement Learning Through Preference-Guided Stochastic Exploration","publication_year":2023,"publication_date":"2023-10-03","ids":{"openalex":"https://openalex.org/W4387303358","doi":"https://doi.org/10.1109/tnnls.2023.3317628","pmid":"https://pubmed.ncbi.nlm.nih.gov/37788189"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3317628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3317628","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101476556","display_name":"Wenhui Huang","orcid":"https://orcid.org/0000-0001-7212-027X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenhui Huang","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7212-027X","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438393","display_name":"Cong Zhang","orcid":"https://orcid.org/0000-0002-8434-1181"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cong Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8434-1181","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044215622","display_name":"Jingda Wu","orcid":"https://orcid.org/0000-0002-7336-4492"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingda Wu","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7336-4492","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061259393","display_name":"Xiangkun He","orcid":"https://orcid.org/0000-0001-9818-0879"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangkun He","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9818-0879","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685752","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-9745-664X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072073374","display_name":"Chen Lv","orcid":"https://orcid.org/0000-0001-6897-4512"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6897-4512","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.6966,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91658597,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"35","issue":"12","first_page":"18553","last_page":"18564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9861000180244446,"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/T12676","display_name":"Machine Learning and ELM","score":0.9861000180244446,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9817000031471252,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9771999716758728,"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/notation","display_name":"Notation","score":0.7250689268112183},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6009767055511475},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5100935101509094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.447546124458313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4037879407405853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.402383416891098},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3464711308479309},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33928099274635315},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3257371187210083},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17195868492126465},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.15393629670143127},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.13271275162696838}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.7250689268112183},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6009767055511475},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5100935101509094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.447546124458313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4037879407405853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.402383416891098},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3464711308479309},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33928099274635315},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3257371187210083},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17195868492126465},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.15393629670143127},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.13271275162696838},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3317628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3317628","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37788189","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37788189","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":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2094387729","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2799256316","https://openalex.org/W2896089337","https://openalex.org/W2904246096","https://openalex.org/W2919115771","https://openalex.org/W3008354258","https://openalex.org/W3012783233","https://openalex.org/W3127561923","https://openalex.org/W3187550742","https://openalex.org/W3193544356","https://openalex.org/W3196755144","https://openalex.org/W4210870706","https://openalex.org/W4226257065","https://openalex.org/W4282944694","https://openalex.org/W4312368000","https://openalex.org/W4317553819","https://openalex.org/W4321617947","https://openalex.org/W6676172287","https://openalex.org/W6683204974","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6734517396","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6745497480","https://openalex.org/W6747473740","https://openalex.org/W6751629939","https://openalex.org/W6754005058","https://openalex.org/W6771936881","https://openalex.org/W6780559895","https://openalex.org/W6848849564"],"related_works":["https://openalex.org/W2338700700","https://openalex.org/W2386767533","https://openalex.org/W2110390863","https://openalex.org/W347180939","https://openalex.org/W3046926816","https://openalex.org/W2090686886","https://openalex.org/W2332694326","https://openalex.org/W4249089511","https://openalex.org/W2913338188","https://openalex.org/W4307311521"],"abstract_inverted_index":{"Stochastic":[0],"exploration":[1,18,51,57,137],"is":[2,77],"the":[3,6,9,30,39,83,91,95,99,107,113,121,128,134,139,171,176,193],"key":[4],"to":[5,142,166],"success":[7],"of":[8,25,71,75,80,130,195,201],"deep":[10],"-network":[11],"(DQN)":[12],"algorithm.":[13],"However,":[14],"most":[15],"existing":[16],"stochastic":[17],"approaches":[19],"either":[20],"explore":[21],"actions":[22,148],"heuristically":[23],"regardless":[24],"their":[26],"values":[27,151,161],"or":[28],"couple":[29],"sampling":[31],"with":[32,127,149,159,182],"values,":[33],"which":[34,76,88],"inevitably":[35],"introduce":[36],"bias":[37],"into":[38],"learning":[40],"process.":[41],"In":[42],"this":[43],"article,":[44],"we":[45,65,89],"propose":[46],"a":[47,67,78,164],"novel":[48],"preference-guided":[49,114,135],"-greedy":[50,115,136],"algorithm":[52],"that":[53,98,106,120,147],"can":[54,152],"efficiently":[55],"facilitate":[56],"for":[58,112],"DQN":[59,100,140,184],"without":[60],"introducing":[61],"additional":[62],"bias.":[63],"Specifically,":[64],"design":[66],"dual":[68],"architecture":[69],"consisting":[70],"two":[72],"branches,":[73],"one":[74],"copy":[79],"DQN,":[81],"namely,":[82],"branch.":[84],"The":[85],"other":[86],"branch,":[87,93],"call":[90],"preference":[92,97,124],"learns":[94],"action":[96,123],"implicitly":[101],"follows.":[102],"We":[103,173],"theoretically":[104],"prove":[105],"policy":[108,116],"improvement":[109],"theorem":[110],"holds":[111],"and":[117,157,203],"experimentally":[118],"show":[119],"inferred":[122],"distribution":[125],"aligns":[126],"landscape":[129],"corresponding":[131],"values.":[132],"Intuitively,":[133],"motivates":[138],"agent":[141],"take":[143],"diverse":[144],"actions,":[145],"so":[146],"larger":[150],"be":[153,167],"sampled":[154],"more":[155],"frequently,":[156],"those":[158],"smaller":[160],"still":[162],"have":[163],"chance":[165],"explored,":[168],"thus":[169],"encouraging":[170],"exploration.":[172],"comprehensively":[174],"evaluate":[175],"proposed":[177,197],"method":[178,198],"by":[179],"benchmarking":[180],"it":[181],"well-known":[183],"variants":[185],"in":[186,199],"nine":[187],"different":[188],"environments.":[189],"Extensive":[190],"results":[191],"confirm":[192],"superiority":[194],"our":[196],"terms":[200],"performance":[202],"convergence":[204],"speed.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}