{"id":"https://openalex.org/W4413393686","doi":"https://doi.org/10.23919/acc63710.2025.11107904","title":"Online Reinforcement Learning with Passive Memory","display_name":"Online Reinforcement Learning with Passive Memory","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393686","doi":"https://doi.org/10.23919/acc63710.2025.11107904"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107904","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057351003","display_name":"Anay Pattanaik","orcid":"https://orcid.org/0000-0002-5664-672X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anay Pattanaik","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Computer Science and Coordinated Science Laboratory,Urbana,IL,USA,61801"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Computer Science and Coordinated Science Laboratory,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065423139","display_name":"Lav R. Varshney","orcid":"https://orcid.org/0000-0003-2798-5308"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lav R. Varshney","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering and Coordinated Science Laboratory,Urbana,IL,USA,61801"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Department of Electrical and Computer Engineering and Coordinated Science Laboratory,Urbana,IL,USA,61801","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3551","last_page":"3557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7720000147819519,"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":0.7720000147819519,"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":0.6868000030517578,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.6452999711036682,"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":0.7858468890190125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246168851852417},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5347843170166016},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39455676078796387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2842181324958801},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.157260924577713}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7858468890190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246168851852417},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5347843170166016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39455676078796387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2842181324958801},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.157260924577713},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107904","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W207039890","https://openalex.org/W1511694993","https://openalex.org/W1651908058","https://openalex.org/W2145339207","https://openalex.org/W2346736747","https://openalex.org/W2746553466","https://openalex.org/W2973229164","https://openalex.org/W3107053627","https://openalex.org/W4245577611","https://openalex.org/W4248292163","https://openalex.org/W4386710799"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"an":[3],"online":[4,18],"reinforcement":[5],"learning":[6],"algorithm":[7],"that":[8,22,35,44],"leverages":[9],"pre-collected":[10],"data":[11],"(passive":[12],"memory)":[13],"from":[14],"the":[15,52],"environment":[16],"for":[17,33],"interaction.":[19],"We":[20],"show":[21,43],"using":[23],"passive":[24,47],"memory":[25,48],"improves":[26],"performance":[27],"and":[28,58,64],"further":[29],"provide":[30],"theoretical":[31],"guarantees":[32],"regret":[34],"turns":[36],"out":[37],"to":[38],"be":[39],"near-minimax":[40],"optimal.":[41],"Results":[42],"quality":[45],"of":[46,51],"determines":[49],"sub-optimality":[50],"incurred":[53],"regret.":[54],"The":[55],"proposed":[56],"approach":[57],"results":[59],"hold":[60],"in":[61],"both":[62],"continuous":[63],"discrete":[65],"state-action":[66],"spaces.":[67]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}