{"id":"https://openalex.org/W4405400011","doi":"https://doi.org/10.1007/s11704-024-3946-y","title":"Offline model-based reinforcement learning with causal structured world models","display_name":"Offline model-based reinforcement learning with causal structured world models","publication_year":2024,"publication_date":"2024-12-14","ids":{"openalex":"https://openalex.org/W4405400011","doi":"https://doi.org/10.1007/s11704-024-3946-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11704-024-3946-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-024-3946-y","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","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/A5037968482","display_name":"Zhengmao Zhu","orcid":"https://orcid.org/0000-0002-8734-8020"},"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":"Zhengmao Zhu","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074345072","display_name":"Honglong Tian","orcid":null},"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":"Honglong Tian","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081695832","display_name":"Xionghui Chen","orcid":"https://orcid.org/0000-0002-4866-0951"},"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":"Xionghui Chen","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342345","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-5317-8414"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["Department of Philosophy, Carnegie Mellon University, Pittsburgh, PA, 15112, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Philosophy, Carnegie Mellon University, Pittsburgh, PA, 15112, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458530","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-8209-2898"},"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":true,"raw_author_name":"Yang Yu","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, Nanjing, 210023, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100458530"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":0.729,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77156632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"4","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":0.9983999729156494,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9628000259399414,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9585000276565552,"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/computer-science","display_name":"Computer science","score":0.8411136865615845},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8154455423355103},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7504241466522217},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6875472068786621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.683957576751709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.636836051940918},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6340422630310059},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.5947137475013733},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.5582112669944763},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5190854072570801},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5159662365913391},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.17493009567260742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411136865615845},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8154455423355103},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7504241466522217},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6875472068786621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.683957576751709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.636836051940918},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6340422630310059},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.5947137475013733},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5582112669944763},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5190854072570801},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5159662365913391},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.17493009567260742},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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:10.1007/s11704-024-3946-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-024-3946-y","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","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":24,"referenced_works":["https://openalex.org/W178169250","https://openalex.org/W567831624","https://openalex.org/W774034202","https://openalex.org/W1511986666","https://openalex.org/W1583837637","https://openalex.org/W2171866865","https://openalex.org/W2396335173","https://openalex.org/W2539402368","https://openalex.org/W2582998992","https://openalex.org/W2599276130","https://openalex.org/W2602856279","https://openalex.org/W2622408375","https://openalex.org/W2799352588","https://openalex.org/W2904730732","https://openalex.org/W2911293880","https://openalex.org/W2913954081","https://openalex.org/W2914304175","https://openalex.org/W2981030070","https://openalex.org/W3016525976","https://openalex.org/W4234173777","https://openalex.org/W4288095810","https://openalex.org/W4299515571","https://openalex.org/W4302423442","https://openalex.org/W4365799809"],"related_works":["https://openalex.org/W2161504683","https://openalex.org/W2093587551","https://openalex.org/W2477954850","https://openalex.org/W4307313254","https://openalex.org/W2740541622","https://openalex.org/W2784306284","https://openalex.org/W2124859246","https://openalex.org/W1985230145","https://openalex.org/W3169419898","https://openalex.org/W4281686999"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
