{"id":"https://openalex.org/W4415777777","doi":"https://doi.org/10.1007/s11432-024-4403-7","title":"Learning by doing: an online causal reinforcement learning framework with causal-aware policy","display_name":"Learning by doing: an online causal reinforcement learning framework with causal-aware policy","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4415777777","doi":"https://doi.org/10.1007/s11432-024-4403-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11432-024-4403-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-024-4403-7","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1674-733X","issn":["1674-733X","1869-1919"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","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/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"]},{"id":"https://openalex.org/I4210087590","display_name":"Huzhou Vocational and Technical College","ror":"https://ror.org/002hfez23","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210087590"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruichu Cai","raw_affiliation_strings":["Pazhou Laboratory (Huangpu), Guangzhou, 510555, China","School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pazhou Laboratory (Huangpu), Guangzhou, 510555, China","institution_ids":["https://openalex.org/I4210087590"]},{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595405","display_name":"Siyang Huang","orcid":"https://orcid.org/0009-0002-3828-040X"},"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":"Siyang Huang","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100574061","display_name":"Jie Qiao","orcid":null},"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":"Jie Qiao","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344522","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-0065-3610"},"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":"Wei Chen","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642516","display_name":"Yan Zeng","orcid":"https://orcid.org/0000-0003-2275-6354"},"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, 102401, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Beijing Technology and Business University, Beijing, 102401, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113115892","display_name":"Keli Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Keli Zhang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Shenzhen, 518116, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Shenzhen, 518116, China","institution_ids":["https://openalex.org/I4210159102","https://openalex.org/I2250955327"]}]},{"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, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100190, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411381","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-5204-2929"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210093, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210093, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092002405","display_name":"Zhifeng Hao","orcid":null},"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, 515063, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science, Shantou University, Shantou, 515063, China","institution_ids":["https://openalex.org/I32574673"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5076948208"],"corresponding_institution_ids":["https://openalex.org/I139024713","https://openalex.org/I4210087590"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16032231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.46369999647140503,"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":0.46369999647140503,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.16220000386238098,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.027300000190734863,"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/interpretability","display_name":"Interpretability","score":0.7391999959945679},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.5616999864578247},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5583000183105469},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.5120999813079834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4569999873638153},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.4180000126361847},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.4106999933719635}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7391999959945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740000009536743},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.5120999813079834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4569999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.4180000126361847},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.2797999978065491},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.2761000096797943},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11432-024-4403-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-024-4403-7","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1674-733X","issn":["1674-733X","1869-1919"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1976659148","https://openalex.org/W1977655452","https://openalex.org/W1980035368","https://openalex.org/W2073787051","https://openalex.org/W2143891888","https://openalex.org/W2150291618","https://openalex.org/W2257979135","https://openalex.org/W2557632452","https://openalex.org/W2580460079","https://openalex.org/W2808914202","https://openalex.org/W2964254462","https://openalex.org/W3200466256","https://openalex.org/W4282942756","https://openalex.org/W4302423442","https://openalex.org/W4391259941"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-11-03T00:00:00"}
