{"id":"https://openalex.org/W4407949229","doi":"https://doi.org/10.1109/cdc56724.2024.10885945","title":"Robust Q-Learning under Corrupted Rewards","display_name":"Robust Q-Learning under Corrupted Rewards","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949229","doi":"https://doi.org/10.1109/cdc56724.2024.10885945"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10885945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5023891178","display_name":"Sreejeet Maity","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sreejeet Maity","raw_affiliation_strings":["North Carolina State University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101651422","display_name":"Aritra Mitra","orcid":"https://orcid.org/0000-0002-0472-284X"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aritra Mitra","raw_affiliation_strings":["North Carolina State University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023891178"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25517336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1181","last_page":"1186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.8669000267982483,"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/T12676","display_name":"Machine Learning and ELM","score":0.8669000267982483,"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/T10057","display_name":"Face and Expression Recognition","score":0.8550999760627747,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.8306999802589417,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6529536247253418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43168386816978455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6529536247253418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43168386816978455}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10885945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1999254175","https://openalex.org/W2147750403","https://openalex.org/W2150147323","https://openalex.org/W2794925984","https://openalex.org/W2963616027","https://openalex.org/W3003165689","https://openalex.org/W3126729338","https://openalex.org/W4233061323","https://openalex.org/W4249736682","https://openalex.org/W4366692289","https://openalex.org/W4386089604","https://openalex.org/W4391410851","https://openalex.org/W6677753333","https://openalex.org/W6677826109","https://openalex.org/W6678494045","https://openalex.org/W6748232849","https://openalex.org/W6754906582","https://openalex.org/W6758937863","https://openalex.org/W6759790382","https://openalex.org/W6763048320","https://openalex.org/W6874014613"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"a":[4,54,64,94,119,138],"surge":[5],"of":[6,13,21,33,48,67,134],"interest":[7],"in":[8,24,30],"analyzing":[9],"the":[10,19,31,46,49,68,81,132,146],"non-asymptotic":[11],"behavior":[12],"model-free":[14],"reinforcement":[15],"learning":[16,99],"algorithms.":[17],"However,":[18],"performance":[20],"such":[22,28,76],"algorithms":[23],"non-ideal":[25],"environments":[26],"-":[27,36],"as":[29],"presence":[32],"corrupted":[34],"rewards":[35],"is":[37],"poorly":[38],"understood.":[39],"Motivated":[40],"by":[41,73],"this":[42],"gap,":[43],"we":[44,117],"investigate":[45],"robustness":[47],"celebrated":[50],"Q-learning":[51],"algorithm":[52,85,100,125],"to":[53,86,106,137],"strong-contamination":[55],"attack":[56,78],"model,":[57],"where":[58],"an":[59,77],"adversary":[60],"can":[61,79],"arbitrarily":[62,88],"perturb":[63],"small":[65,139],"fraction":[66],"observed":[69],"rewards.":[70],"We":[71,91],"start":[72],"proving":[74],"that":[75,101,126,143],"cause":[80],"vanilla":[82],"Q":[83],"-learning":[84],"incur":[87],"large":[89],"errors.":[90],"then":[92],"develop":[93],"novel":[95],"robust":[96,108],"synchronous":[97],"Q-":[98],"uses":[102],"historical":[103],"reward":[104],"data":[105],"construct":[107],"empirical":[109],"Bellman":[110],"operators":[111],"at":[112],"each":[113],"time":[114],"step.":[115],"Finally,":[116],"prove":[118],"finite-time":[120],"convergence":[121],"rate":[122],"for":[123],"our":[124],"matches":[127],"known":[128],"state-of-the-art":[129],"bounds":[130],"(in":[131],"absence":[133],"attacks)":[135],"up":[136],"inevitable":[140],"error":[141],"term":[142],"scales":[144],"with":[145],"adversarial":[147],"corruption":[148],"fraction.":[149]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}