{"id":"https://openalex.org/W4415795377","doi":"https://doi.org/10.52202/079017-3966","title":"Identifying Latent State-Transition Processes for Individualized Reinforcement Learning","display_name":"Identifying Latent State-Transition Processes for Individualized Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415795377","doi":"https://doi.org/10.52202/079017-3966"},"language":"en","primary_location":{"id":"doi:10.52202/079017-3966","doi":"https://doi.org/10.52202/079017-3966","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3966","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5100312238","display_name":"Yuewen Sun","orcid":"https://orcid.org/0009-0007-1512-8188","observed_orcids":["https://orcid.org/0009-0007-1512-8188"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuewen Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071784683","display_name":"Biwei Huang","orcid":"https://orcid.org/0009-0005-5867-7254","observed_orcids":["https://orcid.org/0009-0005-5867-7254"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biwei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100309544","display_name":"Yu Yao","orcid":"https://orcid.org/0009-0002-3343-3235","observed_orcids":["https://orcid.org/0009-0002-3343-3235"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085606015","display_name":"Donghuo Zeng","orcid":"https://orcid.org/0000-0002-6425-6270","observed_orcids":["https://orcid.org/0000-0002-6425-6270"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghuo Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079198353","display_name":"Xinshuai Dong","orcid":"https://orcid.org/0000-0002-8593-0586","observed_orcids":["https://orcid.org/0000-0002-8593-0586"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinshuai Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113095175","display_name":"Songyao Jin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songyao Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Boyang Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014746910","display_name":"Roberto Legaspi","orcid":"https://orcid.org/0000-0001-8909-635X","observed_orcids":["https://orcid.org/0000-0001-8909-635X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Legaspi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013855705","display_name":"Kazushi Ikeda","orcid":"https://orcid.org/0009-0000-9563-760X","observed_orcids":["https://orcid.org/0009-0000-9563-760X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazushi Ikeda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047533473","display_name":"Peter Spirtes","orcid":"https://orcid.org/0000-0002-1385-190X","observed_orcids":["https://orcid.org/0000-0002-1385-190X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Spirtes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055236544","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0197-8778","observed_orcids":["https://orcid.org/0000-0002-0197-8778"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29070707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"124887","last_page":"124924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9624000191688538,"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":0.9624000191688538,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.008299999870359898,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalized-learning","display_name":"personalized learning","score":0.7009999752044678},{"id":"https://openalex.org/keywords/individual-differences","display_name":"individual differences","score":0.3140000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46939998865127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562000036239624},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30410000681877136},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.52202/079017-3966","doi":"https://doi.org/10.52202/079017-3966","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3966","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133240338","https://openalex.org/W2579807083","https://openalex.org/W7074002762","https://openalex.org/W7133239307","https://openalex.org/W7196931009","https://openalex.org/W7196948040","https://openalex.org/W4415798684","https://openalex.org/W2803178532","https://openalex.org/W7196922813","https://openalex.org/W3213878263"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-03T00:00:00"}