{"id":"https://openalex.org/W4401693786","doi":"https://doi.org/10.1109/isit57864.2024.10619458","title":"Towards General Function Approximation in Nonstationary Reinforcement Learning","display_name":"Towards General Function Approximation in Nonstationary Reinforcement Learning","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4401693786","doi":"https://doi.org/10.1109/isit57864.2024.10619458"},"language":"en","primary_location":{"id":"doi:10.1109/isit57864.2024.10619458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit57864.2024.10619458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-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/A5057599205","display_name":"Songtao Feng","orcid":"https://orcid.org/0000-0002-7773-5406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songtao Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101993864","display_name":"Ming Yin","orcid":"https://orcid.org/0000-0002-7037-1048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025491239","display_name":"Ruiquan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiquan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394392","display_name":"Yu-Xiang Wang","orcid":"https://orcid.org/0000-0002-6403-212X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Xiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645589","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-6009-864X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384384","display_name":"Yingbin Liang","orcid":"https://orcid.org/0000-0003-2631-4262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingbin Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":0.10764588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9564999938011169,"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":0.9564999938011169,"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-learning","display_name":"Reinforcement learning","score":0.7494441270828247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.601323127746582},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5495948195457458},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.542709469795227},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3837236166000366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37782132625579834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22179728746414185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12408450245857239}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7494441270828247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.601323127746582},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5495948195457458},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.542709469795227},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3837236166000366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37782132625579834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22179728746414185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12408450245857239},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit57864.2024.10619458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit57864.2024.10619458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1981773323","https://openalex.org/W2074680702","https://openalex.org/W2151161180","https://openalex.org/W2156211713","https://openalex.org/W2158130000","https://openalex.org/W2162926979","https://openalex.org/W2562337727","https://openalex.org/W2575705757","https://openalex.org/W2902907165","https://openalex.org/W2949910245","https://openalex.org/W2953303875","https://openalex.org/W2953305686","https://openalex.org/W2959895084","https://openalex.org/W2987195113","https://openalex.org/W2998187693","https://openalex.org/W4247692611","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3021988786","https://openalex.org/W3099311996","https://openalex.org/W2963971282"],"abstract_inverted_index":{"Function":[0],"approximation":[1,26,38],"has":[2,87],"experienced":[3],"significant":[4],"success":[5],"in":[6,84,101],"the":[7,53,60,78,92,102],"field":[8],"of":[9,16,49,67],"reinforcement":[10],"learning":[11],"(RL).":[12],"Despite":[13],"a":[14,47,64],"handful":[15],"progress":[17],"on":[18],"developing":[19],"theory":[20],"for":[21,32,95],"Nonstationary":[22],"RL":[23,34],"with":[24,35],"function":[25,37],"under":[27],"structural":[28],"assumptions,":[29],"existing":[30,79,93],"work":[31],"nonstationary":[33,96],"general":[36],"is":[39],"still":[40],"limited.":[41],"In":[42],"this":[43],"work,":[44],"we":[45],"propose":[46],"UCB-type":[48],"algorithm":[50,82],"LSVI-Nonstationary":[51,58],"following":[52],"popular":[54],"least-square-value-iteration":[55],"(LSVI)":[56],"framework.":[57],"features":[59],"restart":[61],"mechanism":[62],"and":[63,73,98],"new":[65],"design":[66],"bonus":[68],"term":[69],"to":[70,90],"handle":[71],"nonstationarity,":[72],"performs":[74],"no":[75],"worse":[76],"than":[77],"confidence-set":[80],"based":[81],"SW-OPEA":[83],"[1],":[85],"which":[86],"been":[88],"shown":[89],"outperform":[91],"algorithms":[94],"linear":[97],"tabular":[99],"MDPs":[100],"small":[103],"variation":[104],"budget":[105],"setting.":[106]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}