{"id":"https://openalex.org/W4404809951","doi":"https://doi.org/10.1109/tnnls.2024.3403001","title":"A Survey on Causal Reinforcement Learning","display_name":"A Survey on Causal Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-28","ids":{"openalex":"https://openalex.org/W4404809951","doi":"https://doi.org/10.1109/tnnls.2024.3403001","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030342"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3403001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3403001","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/A5035831769","display_name":"Yan Zeng","orcid":"https://orcid.org/0000-0001-7721-2560"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zeng","raw_affiliation_strings":["School of Mathematics and Statistics, Beijing Technology and Business University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7721-2560","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076948208","display_name":"Ruichu Cai","orcid":"https://orcid.org/0000-0001-8972-167X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruichu Cai","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8972-167X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3546-6305","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115593380","display_name":"Libo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Huang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4479-5840","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhifeng Hao","orcid":"https://orcid.org/0000-0002-9731-1504"},"institutions":[{"id":"https://openalex.org/I32574673","display_name":"Shantou University","ror":"https://ror.org/01a099706","country_code":"CN","type":"education","lineage":["https://openalex.org/I32574673"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Hao","raw_affiliation_strings":["College of Science, Shantou University, Shantou, China"],"raw_orcid":"https://orcid.org/0000-0002-9731-1504","affiliations":[{"raw_affiliation_string":"College of Science, Shantou University, Shantou, China","institution_ids":["https://openalex.org/I32574673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3099,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98365027,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"36","issue":"4","first_page":"5942","last_page":"5962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7946000099182129,"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":0.7946000099182129,"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","display_name":"Reinforcement","score":0.6352177858352661},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.5283477902412415},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4519587755203247},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3256564736366272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.29843664169311523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2821948528289795},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.23047733306884766}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6352177858352661},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5283477902412415},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4519587755203247},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3256564736366272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29843664169311523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2821948528289795},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.23047733306884766}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"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":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","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":"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":"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":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","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":"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":"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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3403001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3403001","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:40030342","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030342","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":[{"id":"https://openalex.org/G2503486912","display_name":null,"funder_award_id":"61976052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4471167475","display_name":"\u975e\u7a33\u6001\u793e\u4ea4\u7f51\u7edc\u7528\u6237\u884c\u4e3a\u7684\u56e0\u679c\u673a\u5236\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61876043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5654944882","display_name":null,"funder_award_id":"2018AAA0102900","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G7721746300","display_name":null,"funder_award_id":"62306019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8007181506","display_name":null,"funder_award_id":"62122022","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"},{"id":"https://openalex.org/G8734588712","display_name":null,"funder_award_id":"2022M711812","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":203,"referenced_works":["https://openalex.org/W1517993545","https://openalex.org/W1655999712","https://openalex.org/W1965834173","https://openalex.org/W1975062332","https://openalex.org/W1977655452","https://openalex.org/W1999874108","https://openalex.org/W2051944318","https://openalex.org/W2064903582","https://openalex.org/W2070469928","https://openalex.org/W2093947494","https://openalex.org/W2104281034","https://openalex.org/W2132917208","https://openalex.org/W2135404705","https://openalex.org/W2145339207","https://openalex.org/W2150291618","https://openalex.org/W2158782408","https://openalex.org/W2159805452","https://openalex.org/W2165612525","https://openalex.org/W2168175751","https://openalex.org/W2297288734","https://openalex.org/W2396961959","https://openalex.org/W2491632691","https://openalex.org/W2507814050","https://openalex.org/W2570113340","https://openalex.org/W2604382266","https://openalex.org/W2617547828","https://openalex.org/W2624816748","https://openalex.org/W2740396279","https://openalex.org/W2746553466","https://openalex.org/W2747984964","https://openalex.org/W2754517384","https://openalex.org/W2766447205","https://openalex.org/W2802494201","https://openalex.org/W2808914202","https://openalex.org/W2810602713","https://openalex.org/W2904362269","https://openalex.org/W2947630374","https://openalex.org/W2948579453","https://openalex.org/W2951625652","https://openalex.org/W2954682669","https://openalex.org/W2962685611","https://openalex.org/W2962872206","https://openalex.org/W2963654596","https://openalex.org/W2969873918","https://openalex.org/W2982316857","https://openalex.org/W2997054006","https://openalex.org/W2998548529","https://openalex.org/W3009593063","https://openalex.org/W3023586494","https://openalex.org/W3038822267","https://openalex.org/W3092106817","https://openalex.org/W3100789280","https://openalex.org/W3101780148","https://openalex.org/W3124999902","https://openalex.org/W3130150161","https://openalex.org/W3135588948","https://openalex.org/W3150893739","https://openalex.org/W3154564281","https://openalex.org/W3155375080","https://openalex.org/W3157189937","https://openalex.org/W3165503008","https://openalex.org/W3182663209","https://openalex.org/W3188252770","https://openalex.org/W3189150484","https://openalex.org/W3191081139","https://openalex.org/W3197421332","https://openalex.org/W3200466256","https://openalex.org/W3206889352","https://openalex.org/W3209710554","https://openalex.org/W3216656735","https://openalex.org/W4205513846","https://openalex.org/W4224317003","https://openalex.org/W4226203009","https://openalex.org/W4237591687","https://openalex.org/W4244067982","https://openalex.org/W4250375351","https://openalex.org/W4283452782","https://openalex.org/W4283796568","https://openalex.org/W4283820834","https://openalex.org/W4302423442","https://openalex.org/W4302761554","https://openalex.org/W4312573894","https://openalex.org/W4379527413","https://openalex.org/W4385834352","https://openalex.org/W4389584650","https://openalex.org/W4391259941","https://openalex.org/W4403326725","https://openalex.org/W6631552155","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6679853467","https://openalex.org/W6680657880","https://openalex.org/W6681478256","https://openalex.org/W6681517296","https://openalex.org/W6682361391","https://openalex.org/W6683195989","https://openalex.org/W6684389209","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6686823217","https://openalex.org/W6692846177","https://openalex.org/W6696380822","https://openalex.org/W6711306941","https://openalex.org/W6716227286","https://openalex.org/W6716474083","https://openalex.org/W6726651112","https://openalex.org/W6732665253","https://openalex.org/W6734330393","https://openalex.org/W6735810065","https://openalex.org/W6739416393","https://openalex.org/W6741002519","https://openalex.org/W6742245242","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6748519856","https://openalex.org/W6751220891","https://openalex.org/W6751494529","https://openalex.org/W6752252196","https://openalex.org/W6753192631","https://openalex.org/W6753611882","https://openalex.org/W6754586084","https://openalex.org/W6755655695","https://openalex.org/W6756341295","https://openalex.org/W6757212879","https://openalex.org/W6757835162","https://openalex.org/W6757988370","https://openalex.org/W6758763022","https://openalex.org/W6760368646","https://openalex.org/W6763081524","https://openalex.org/W6763168094","https://openalex.org/W6764053384","https://openalex.org/W6765905676","https://openalex.org/W6766022639","https://openalex.org/W6766883460","https://openalex.org/W6769196198","https://openalex.org/W6771638272","https://openalex.org/W6773147725","https://openalex.org/W6773793740","https://openalex.org/W6774121513","https://openalex.org/W6774858212","https://openalex.org/W6775721199","https://openalex.org/W6776438516","https://openalex.org/W6777656069","https://openalex.org/W6778306200","https://openalex.org/W6778979777","https://openalex.org/W6779511865","https://openalex.org/W6779619272","https://openalex.org/W6779757217","https://openalex.org/W6779827379","https://openalex.org/W6780164128","https://openalex.org/W6780215732","https://openalex.org/W6780369355","https://openalex.org/W6781045951","https://openalex.org/W6784188657","https://openalex.org/W6784313279","https://openalex.org/W6784915420","https://openalex.org/W6785172053","https://openalex.org/W6785402367","https://openalex.org/W6785604037","https://openalex.org/W6786132411","https://openalex.org/W6787532554","https://openalex.org/W6788053055","https://openalex.org/W6790458829","https://openalex.org/W6790695711","https://openalex.org/W6790971907","https://openalex.org/W6791413555","https://openalex.org/W6794590674","https://openalex.org/W6795694517","https://openalex.org/W6795769471","https://openalex.org/W6796190733","https://openalex.org/W6796333007","https://openalex.org/W6796468389","https://openalex.org/W6796693993","https://openalex.org/W6797360712","https://openalex.org/W6797910908","https://openalex.org/W6798256207","https://openalex.org/W6799730904","https://openalex.org/W6800515976","https://openalex.org/W6800637531","https://openalex.org/W6802151480","https://openalex.org/W6802558061","https://openalex.org/W6802584362","https://openalex.org/W6802920152","https://openalex.org/W6803185288","https://openalex.org/W6803318371","https://openalex.org/W6803821237","https://openalex.org/W6804028279","https://openalex.org/W6804112460","https://openalex.org/W6810310382","https://openalex.org/W6810672005","https://openalex.org/W6838635778","https://openalex.org/W6839094154","https://openalex.org/W6839095618","https://openalex.org/W6839131492","https://openalex.org/W6839353417","https://openalex.org/W6841247348","https://openalex.org/W6846209249","https://openalex.org/W6846437847","https://openalex.org/W6855146449","https://openalex.org/W6861805697","https://openalex.org/W6866487597","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"While":[0],"reinforcement":[1],"learning":[2,137],"(RL)":[3],"achieves":[4],"tremendous":[5],"success":[6],"in":[7,105,114],"sequential":[8],"decision-making":[9],"problems":[10],"of":[11,19,25,46,59,74,116,119,145,151,177],"many":[12,28],"domains,":[13],"it":[14,57],"still":[15],"faces":[16],"key":[17],"challenges":[18,52],"data":[20],"inefficiency":[21],"and":[22,48,62,77,139,161],"the":[23,34,44,51,79,90,117,124,158,174],"lack":[24],"interpretability.":[26],"Interestingly,":[27],"researchers":[29],"have":[30],"leveraged":[31],"insights":[32],"from":[33,53,82,123],"causality":[35,47,83],"literature":[36],"recently,":[37],"bringing":[38],"forth":[39],"flourishing":[40],"works":[41],"to":[42,64,98],"unify":[43],"merits":[45],"address":[49],"well":[50],"RL.":[54,85],"As":[55],"such,":[56],"is":[58,103],"great":[60],"necessity":[61],"significance":[63],"collate":[65],"these":[66],"causal":[67,152],"RL":[68],"(CRL)":[69],"works,":[70],"offer":[71],"a":[72,148],"review":[73],"CRL":[75,92],"methods,":[76],"investigate":[78],"potential":[80],"functionality":[81],"toward":[84],"In":[86],"particular,":[87],"we":[88,156,165],"divide":[89],"existing":[91],"approaches":[93],"into":[94],"two":[95],"categories":[96],"according":[97],"whether":[99],"their":[100],"causality-based":[101],"information":[102],"given":[104],"advance":[106],"or":[107],"not.":[108],"We":[109],"further":[110],"analyze":[111],"each":[112],"category":[113],"terms":[115],"formalization":[118],"different":[120],"models,":[121],"ranging":[122],"Markov":[125],"decision":[126],"process":[127],"(MDP),":[128],"partially":[129],"observed":[130],"MDP":[131],"(POMDP),":[132],"multiarmed":[133],"bandits":[134],"(MABs),":[135],"imitation":[136],"(IL),":[138],"dynamic":[140],"treatment":[141],"regime":[142],"(DTR).":[143],"Each":[144],"them":[146],"represents":[147],"distinct":[149],"type":[150],"graphical":[153],"illustration.":[154],"Moreover,":[155],"summarize":[157],"evaluation":[159],"matrices":[160],"open":[162],"sources,":[163],"while":[164],"discuss":[166],"emerging":[167],"applications,":[168],"along":[169],"with":[170],"promising":[171],"prospects":[172],"for":[173],"future":[175],"development":[176],"CRL.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}