{"id":"https://openalex.org/W4393372852","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10477059","title":"Predictive Estimation for Reinforcement Learning with Time-Varying Reward Functions","display_name":"Predictive Estimation for Reinforcement Learning with Time-Varying Reward Functions","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393372852","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10477059"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10477059","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ieeeconf59524.2023.10477059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","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/A5036900440","display_name":"Abolfazl Hashemi","orcid":"https://orcid.org/0000-0002-8421-4270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abolfazl Hashemi","raw_affiliation_strings":["Purdue University,Dept. of Electrical and Computer Engineering,West Lafatyette,USA","Dept. of Electrical and Computer Engineering, Purdue University, West Lafatyette, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Dept. of Electrical and Computer Engineering,West Lafatyette,USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Purdue University, West Lafatyette, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064442263","display_name":"Antesh Upadhyay","orcid":"https://orcid.org/0000-0001-7185-3690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antesh Upadhyay","raw_affiliation_strings":["Purdue University,Dept. of Electrical and Computer Engineering,West Lafatyette,USA","Dept. of Electrical and Computer Engineering, Purdue University, West Lafatyette, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Dept. of Electrical and Computer Engineering,West Lafatyette,USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Purdue University, West Lafatyette, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","issue":null,"first_page":"1377","last_page":"1380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.8637999892234802,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.8637999892234802,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.8159999847412109,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.741599977016449,"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":0.7905705571174622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605511903762817},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6481732130050659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5394479036331177},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49209898710250854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48212528228759766},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17025884985923767},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12517637014389038},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0877566933631897}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7905705571174622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605511903762817},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6481732130050659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5394479036331177},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49209898710250854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48212528228759766},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17025884985923767},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12517637014389038},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0877566933631897},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10477059","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ieeeconf59524.2023.10477059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","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":13,"referenced_works":["https://openalex.org/W1941445455","https://openalex.org/W2098432798","https://openalex.org/W2119567691","https://openalex.org/W2909648661","https://openalex.org/W2991935368","https://openalex.org/W3186637586","https://openalex.org/W4206530644","https://openalex.org/W6638777087","https://openalex.org/W6639381437","https://openalex.org/W6681980492","https://openalex.org/W6690381995","https://openalex.org/W6762773404","https://openalex.org/W6762889291"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"The":[0],"Adversarial":[1],"Markov":[2],"Decision":[3],"Process":[4],"(MDP)":[5],"serves":[6],"as":[7,144],"a":[8,64,82,95,108,121],"framework":[9,18,44],"for":[10,113],"exploring":[11],"unknown":[12],"and":[13,149],"time-varying":[14],"tasks":[15],"within":[16],"the":[17,33,41,47,89,114,127,145],"of":[19,35,68,110],"Reinforcement":[20],"Learning":[21],"(RL).":[22],"However,":[23],"it":[24],"tends":[25],"to":[26,56,93],"yield":[27],"pessimistic":[28],"results":[29],"when":[30],"characterized":[31],"by":[32,106],"concept":[34],"regret.":[36],"This":[37,132],"is":[38,92],"primarily":[39],"because":[40],"adversarial":[42,74],"MDP":[43],"assumes":[45],"that":[46,97],"loss":[48,69,115],"function":[49],"can":[50],"change":[51],"arbitrarily":[52],"from":[53],"one":[54],"episode":[55],"another.":[57],"In":[58,85],"contrast,":[59],"many":[60],"real-world":[61],"scenarios":[62],"exhibit":[63],"more":[65],"predictable":[66],"evolution":[67],"functions":[70],"rather":[71],"than":[72],"an":[73,135],"one.":[75],"To":[76],"tackle":[77],"this":[78,86],"concern,":[79],"we":[80,118],"introduce":[81],"novel":[83],"model.":[84],"new":[87],"model,":[88],"primary":[90],"objective":[91],"develop":[94],"policy":[96,122],"minimizes":[98],"its":[99,104],"regret":[100],"(or":[101],"equivalently,":[102],"maximizes":[103],"reward)":[105],"utilizing":[107],"sequence":[109],"predictive":[111,146],"estimators":[112],"functions.":[116],"Additionally,":[117],"put":[119],"forth":[120],"optimization":[123],"approach":[124],"based":[125],"on":[126],"optimistic":[128,136],"mirror":[129],"descent":[130],"algorithm.":[131],"method":[133],"yields":[134],"expected":[137],"regret,":[138],"which":[139],"gracefully":[140],"decreases":[141],"in":[142],"magnitude":[143],"estimators'":[147],"accuracy":[148],"estimation":[150],"power":[151],"improve.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}