{"id":"https://openalex.org/W4388283439","doi":"https://doi.org/10.1109/tai.2023.3328848","title":"Improved Demonstration-Knowledge Utilization in Reinforcement Learning","display_name":"Improved Demonstration-Knowledge Utilization in Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-03","ids":{"openalex":"https://openalex.org/W4388283439","doi":"https://doi.org/10.1109/tai.2023.3328848"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3328848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3328848","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/A5104857011","display_name":"Yanyu Liu","orcid":"https://orcid.org/0009-0002-8924-592X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanyu Liu","raw_affiliation_strings":["Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653058","display_name":"Yifeng Zeng","orcid":"https://orcid.org/0000-0002-5246-403X"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yifeng Zeng","raw_affiliation_strings":["Department of Computer and Information Sciences, Northumbria University, Newcastle, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Northumbria University, Newcastle, U.K","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082379297","display_name":"Biyang Ma","orcid":"https://orcid.org/0000-0003-1515-6449"},"institutions":[{"id":"https://openalex.org/I9356336","display_name":"Zhangzhou Normal University","ror":"https://ror.org/02vj1vm13","country_code":"CN","type":"education","lineage":["https://openalex.org/I9356336"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biyang Ma","raw_affiliation_strings":["Department of Computer Science, Minnan Normal University, Zhangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Minnan Normal University, Zhangzhou, China","institution_ids":["https://openalex.org/I9356336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085263461","display_name":"Yinghui Pan","orcid":"https://orcid.org/0000-0001-5715-2855"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Pan","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090120348","display_name":"Huifan Gao","orcid":"https://orcid.org/0000-0002-8624-1301"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifan Gao","raw_affiliation_strings":["Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104857813","display_name":"Yuting Zhang","orcid":"https://orcid.org/0009-0002-9675-5987"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Zhang","raw_affiliation_strings":["Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104857011"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.696,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76566703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"5","issue":"5","first_page":"2139","last_page":"2150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9779000282287598,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9726999998092651,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8136485815048218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7968374490737915},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6430022716522217},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6112836003303528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086339950561523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5875535011291504},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5444201231002808},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.45255813002586365},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4437955617904663},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4180833101272583}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8136485815048218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968374490737915},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6430022716522217},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6112836003303528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086339950561523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5875535011291504},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5444201231002808},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.45255813002586365},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4437955617904663},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4180833101272583},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1109/tai.2023.3328848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3328848","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1408262640","display_name":null,"funder_award_id":"62176225","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6952128119","display_name":null,"funder_award_id":"62276168","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7097245526","display_name":null,"funder_award_id":"61836005","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W1965568826","https://openalex.org/W2596874484","https://openalex.org/W2620974420","https://openalex.org/W2740302738","https://openalex.org/W2741122588","https://openalex.org/W2788862220","https://openalex.org/W2798705390","https://openalex.org/W2837605352","https://openalex.org/W2891295326","https://openalex.org/W2962787188","https://openalex.org/W2963438456","https://openalex.org/W3005355833","https://openalex.org/W3015082424","https://openalex.org/W3081243957","https://openalex.org/W3107153805","https://openalex.org/W3133533407","https://openalex.org/W3158253560","https://openalex.org/W3202546516","https://openalex.org/W4221160486","https://openalex.org/W4251436587","https://openalex.org/W4287867830","https://openalex.org/W4298857966","https://openalex.org/W4303448771","https://openalex.org/W6635327058","https://openalex.org/W6637967152","https://openalex.org/W6640174482","https://openalex.org/W6683300800","https://openalex.org/W6684839497","https://openalex.org/W6742461812","https://openalex.org/W6748603076","https://openalex.org/W6750645735","https://openalex.org/W6771807793","https://openalex.org/W6780559895","https://openalex.org/W6787496176","https://openalex.org/W6791194670","https://openalex.org/W6796367035","https://openalex.org/W6801888299","https://openalex.org/W6810137820","https://openalex.org/W6846768894"],"related_works":["https://openalex.org/W2352650970","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2786230833","https://openalex.org/W2130711276","https://openalex.org/W1544514152","https://openalex.org/W2368059979","https://openalex.org/W3009457412","https://openalex.org/W4294753865","https://openalex.org/W2041191585"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,11,57,77,123,154],"has":[2],"made":[3],"great":[4],"success":[5],"in":[6,86,119,145],"recent":[7],"years.":[8],"Generally,":[9],"the":[10,20,56,64,76,80,96,140,152],"process":[12],"requires":[13],"a":[14,47,110,120,131,146],"huge":[15],"amount":[16],"of":[17,103],"interaction":[18],"with":[19],"environment":[21,98],"before":[22],"an":[23],"agent":[24],"can":[25],"achieve":[26],"acceptable":[27],"performance.":[28],"This":[29],"motivates":[30],"many":[31,87],"techniques,":[32],"such":[33],"as":[34,42],"incorporating":[35],"prior":[36,65,141],"knowledge":[37,66,92,117,144],"which":[38],"is":[39,67,82],"usually":[40],"presented":[41],"experts\u2019":[43],"demonstration,":[44],"and":[45,70,99,138,142,156],"using":[46],"probability":[48],"distribution":[49,112,133],"to":[50,54,75,115,134],"represent":[51,135],"state-and-action":[52],"values,":[53],"accelerate":[55],"process.":[58],"The":[59,90,127],"methods":[60],"perform":[61],"well":[62],"when":[63],"genuinely":[68],"correct":[69],"no":[71],"much":[72],"change":[73],"occurs":[74],"environment.":[78],"However,":[79],"requirement":[81],"not":[83,94],"perfectly":[84],"realistic":[85],"complex":[88],"applications.":[89],"demonstration":[91],"may":[93],"reflect":[95],"true":[97],"even":[100],"be":[101],"full":[102],"noise.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108],"introduce":[109],"dynamic":[111],"merging":[113],"method":[114,129,155],"improve":[116],"utilization":[118],"general":[121],"reinforcement":[122],"algorithm,":[124],"namely":[125],"Q-learning.":[126],"new":[128,153],"adapts":[130],"normal":[132],"state-action":[136],"values":[137],"merges":[139],"learned":[143],"discriminative":[147],"way.":[148],"We":[149],"theoretically":[150],"analyze":[151],"demonstrate":[157],"its":[158],"empirical":[159],"performance":[160],"over":[161],"multiple":[162],"problem":[163],"domains.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}