{"id":"https://openalex.org/W3202439292","doi":"https://doi.org/10.1155/2021/7588221","title":"Efficient Reinforcement Learning from Demonstration via Bayesian Network\u2010Based Knowledge Extraction","display_name":"Efficient Reinforcement Learning from Demonstration via Bayesian Network\u2010Based Knowledge Extraction","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3202439292","doi":"https://doi.org/10.1155/2021/7588221","mag":"3202439292","pmid":"https://pubmed.ncbi.nlm.nih.gov/34603434"},"language":"en","primary_location":{"id":"doi:10.1155/2021/7588221","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/7588221","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/7588221.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/cin/2021/7588221.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060909971","display_name":"Yichuan Zhang","orcid":"https://orcid.org/0000-0002-3647-0245"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichuan Zhang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030762555","display_name":"Yixing Lan","orcid":"https://orcid.org/0000-0003-4503-643X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Lan","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055651722","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-5063-6889"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708067","display_name":"Junxiang Li","orcid":"https://orcid.org/0000-0003-0978-3649"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxiang Li","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003590227","display_name":"Yujun Zeng","orcid":"https://orcid.org/0000-0002-5765-684X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujun Zeng","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003590227"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2100,"currency":"USD","value_usd":2100},"apc_paid":{"value":2100,"currency":"USD","value_usd":2100},"fwci":1.2599,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83995972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":"7588221","last_page":"7588221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9947999715805054,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9897000193595886,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8278652429580688},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7829554080963135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.685673713684082},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6688084602355957},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6681299805641174},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6655404567718506},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5477908253669739},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.541706919670105},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4601612091064453},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.45921608805656433},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.4306853413581848},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4130241572856903},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4125421941280365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08530783653259277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278652429580688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7829554080963135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.685673713684082},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6688084602355957},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6681299805641174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6655404567718506},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5477908253669739},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.541706919670105},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4601612091064453},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.45921608805656433},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.4306853413581848},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4130241572856903},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4125421941280365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08530783653259277},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1155/2021/7588221","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/7588221","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/7588221.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},{"id":"pmid:34603434","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34603434","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":"Computational intelligence and neuroscience","raw_type":null},{"id":"pmh:oai:doaj.org/article:d04001187a714cc1acc1d5c293b6718b","is_oa":true,"landing_page_url":"https://doaj.org/article/d04001187a714cc1acc1d5c293b6718b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Intelligence and Neuroscience, Vol 2021 (2021)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:7379380","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8486502","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8486502","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8486502","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Comput Intell Neurosci","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1155/2021/7588221","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/7588221","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/7588221.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3783177029","display_name":null,"funder_award_id":"617034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5196624177","display_name":null,"funder_award_id":"61825305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5966523899","display_name":null,"funder_award_id":"61703418","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202439292.pdf","grobid_xml":"https://content.openalex.org/works/W3202439292.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1511986666","https://openalex.org/W1604268648","https://openalex.org/W1799762961","https://openalex.org/W1965568826","https://openalex.org/W2070879808","https://openalex.org/W2097994458","https://openalex.org/W2123651102","https://openalex.org/W2135511047","https://openalex.org/W2143668817","https://openalex.org/W2145339207","https://openalex.org/W2164114810","https://openalex.org/W2257979135","https://openalex.org/W2275580678","https://openalex.org/W2596874484","https://openalex.org/W2788295351","https://openalex.org/W2798149936","https://openalex.org/W2837605352","https://openalex.org/W2892591172","https://openalex.org/W2897934046","https://openalex.org/W2902332709","https://openalex.org/W2907326933","https://openalex.org/W2909847834","https://openalex.org/W2912802951","https://openalex.org/W2912997088","https://openalex.org/W2962894046","https://openalex.org/W2963277062","https://openalex.org/W2996868001","https://openalex.org/W2998004401","https://openalex.org/W3006087551","https://openalex.org/W3034311880","https://openalex.org/W3037957403","https://openalex.org/W3083252136","https://openalex.org/W3101780148","https://openalex.org/W3102778384","https://openalex.org/W3103256699","https://openalex.org/W3175096084","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4280645561","https://openalex.org/W1671936420"],"abstract_inverted_index":{"Reinforcement":[0,108],"learning":[1,15,146,199],"from":[2,96,110,137],"demonstration":[3,111],"(RLfD)":[4],"is":[5,76,169],"considered":[6],"to":[7,12,46,87,133,182],"be":[8],"a":[9,39,59,103,141,184],"promising":[10],"approach":[11],"improve":[13],"reinforcement":[14],"(RL)":[16],"by":[17,93],"leveraging":[18],"expert":[19],"demonstrations":[20,33,92,138],"as":[21,34],"the":[22,53,89,127,151,158,165,180,193,198],"additional":[23,49],"decision-making":[24],"guidance.":[25],"However,":[26],"most":[27],"existing":[28],"RLfD":[29,105],"methods":[30],"only":[31,78],"regard":[32],"low-level":[35],"knowledge":[36,75,95,145],"instances":[37],"under":[38,206],"certain":[40],"task.":[41],"Demonstrations":[42],"are":[43],"generally":[44],"used":[45],"either":[47],"provide":[48],"rewards":[50],"or":[51],"pretrain":[52],"neural":[54],"network-based":[55],"RL":[56,204],"policy":[57,160,181],"in":[58,64],"supervised":[60],"manner,":[61],"usually":[62],"resulting":[63],"poor":[65],"generalization":[66,222],"capability":[67,223],"and":[68,101,139,147,178,209,224],"weak":[69],"robustness":[70,225],"performance.":[71],"Considering":[72],"that":[73,192,216],"human":[74],"not":[77],"interpretable":[79],"but":[80],"also":[81],"suitable":[82],"for":[83],"generalization,":[84],"we":[85,214],"propose":[86],"exploit":[88],"potential":[90],"of":[91,123,201],"extracting":[94],"them":[97],"via":[98,112],"Bayesian":[99,113,142],"networks":[100],"develop":[102],"novel":[104],"method":[106,120,196,219],"called":[107],"Learning":[109],"Network-based":[114],"Knowledge":[115],"(RLBNK).":[116],"The":[117],"proposed":[118,194],"RLBNK":[119,195,218],"takes":[121],"advantage":[122],"node":[124],"influence":[125],"with":[126,161],"Wasserstein":[128],"distance":[129],"metric":[130],"(NIW)":[131],"algorithm":[132],"obtain":[134],"abstract":[135,152],"concepts":[136],"then":[140],"network":[143],"conducts":[144],"inference":[148],"based":[149],"on":[150],"data":[153],"set,":[154],"which":[155],"will":[156,175],"yield":[157],"coarse":[159,166],"corresponding":[162,202],"confidence.":[163],"Once":[164],"policy's":[167],"confidence":[168],"low,":[170],"another":[171],"RL-based":[172],"refine":[173],"module":[174],"further":[176],"optimize":[177],"fine-tune":[179],"form":[183],"(near)":[185],"optimal":[186],"hybrid":[187],"policy.":[188],"Experimental":[189],"results":[190],"show":[191],"improves":[197],"efficiency":[200],"baseline":[203,227],"algorithms":[205],"both":[207],"normal":[208],"sparse":[210],"reward":[211],"settings.":[212],"Furthermore,":[213],"demonstrate":[215],"our":[217],"delivers":[220],"better":[221],"than":[226],"methods.":[228]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}