{"id":"https://openalex.org/W4408353307","doi":"https://doi.org/10.1109/icassp49660.2025.10889842","title":"Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality","display_name":"Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353307","doi":"https://doi.org/10.1109/icassp49660.2025.10889842"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5114534520","display_name":"Raghav Bongole","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Raghav Bongole","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010481265","display_name":"Amaury Gouverneur","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Amaury Gouverneur","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041149980","display_name":"Borja Rodr\u00edguez-G\u00e1lvez","orcid":"https://orcid.org/0000-0002-0862-1333"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Borja Rodr\u00edguez-G\u00e1lvez","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079492269","display_name":"Tobias J. Oechtering","orcid":"https://orcid.org/0000-0002-0036-9049"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tobias J. Oechtering","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041348422","display_name":"Mikael Skoglund","orcid":"https://orcid.org/0000-0002-7926-5081"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikael Skoglund","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85572815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.6898000240325928,"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/T10320","display_name":"Neural Networks and Applications","score":0.6898000240325928,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6208999752998352,"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/regret","display_name":"Regret","score":0.8745381832122803},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8093292713165283},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.653965175151825},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.6323018670082092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5409866571426392},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4614047110080719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3355213403701782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.322121262550354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21534574031829834},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.17473170161247253}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8745381832122803},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8093292713165283},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.653965175151825},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.6323018670082092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5409866571426392},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4614047110080719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3355213403701782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.322121262550354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21534574031829834},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.17473170161247253}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1570963478","https://openalex.org/W1975610866","https://openalex.org/W2163872159","https://openalex.org/W3116959972","https://openalex.org/W4205710519","https://openalex.org/W4206530644","https://openalex.org/W4221110788","https://openalex.org/W4308216308","https://openalex.org/W4322576475","https://openalex.org/W4386075250","https://openalex.org/W4387178925","https://openalex.org/W6630683246","https://openalex.org/W6633965395","https://openalex.org/W6676077707","https://openalex.org/W6736209634","https://openalex.org/W6751607607","https://openalex.org/W6758061190","https://openalex.org/W6773756054","https://openalex.org/W6795031267","https://openalex.org/W6810918382","https://openalex.org/W6850293355"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W1925875298","https://openalex.org/W4292701710","https://openalex.org/W2147913478","https://openalex.org/W3182145356"],"abstract_inverted_index":{"We":[0,18],"study":[1,50],"agents":[2,38],"acting":[3],"in":[4,64,132,146],"an":[5],"unknown":[6],"environment":[7,45],"where":[8],"the":[9,40,49,95,112,133],"agent\u2019s":[10],"goal":[11],"is":[12],"to":[13,48,98,115],"find":[14],"a":[15,70,128],"robust":[16,20],"policy.":[17],"consider":[19,37],"policies":[21,23],"as":[22,81],"that":[24],"achieve":[25],"high":[26],"cumulative":[27],"rewards":[28],"for":[29,61,140],"all":[30],"possible":[31],"environments.":[32],"To":[33],"this":[34],"end,":[35],"we":[36,90,104],"minimizing":[39],"maximum":[41],"regret":[42,63,97,101,114,118,131],"over":[43],"different":[44],"parameters,":[46],"leading":[47],"of":[51,135],"minimax":[52,62,87,100,106,117,122,130],"regret.":[53],"This":[54],"research":[55],"focuses":[56],"on":[57,75,94,111],"deriving":[58],"information-theoretic":[59,138],"bounds":[60,93,110,139,145],"Markov":[65],"Decision":[66],"Processes":[67],"(MDPs)":[68],"with":[69],"finite":[71],"time":[72],"horizon.":[73],"Building":[74],"concepts":[76],"from":[77],"supervised":[78],"learning,":[79],"such":[80],"minimum":[82],"excess":[83,88],"risk":[84],"(MER)":[85],"and":[86,108,142],"risk,":[89],"use":[91,109],"recent":[92],"Bayesian":[96,113],"derive":[99],"bounds.":[102],"Specifically,":[103],"establish":[105],"theorems":[107],"perform":[116],"analysis":[119],"using":[120],"these":[121,144],"theorems.":[123],"Our":[124],"contributions":[125],"include":[126],"defining":[127],"suitable":[129],"context":[134],"MDPs,":[136],"finding":[137],"it,":[141],"applying":[143],"various":[147],"scenarios.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}