{"id":"https://openalex.org/W4388666884","doi":"https://doi.org/10.1109/allerton58177.2023.10313396","title":"The Reward Biased Method: An Optimism based Approach for Reinforcement Learning","display_name":"The Reward Biased Method: An Optimism based Approach for Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4388666884","doi":"https://doi.org/10.1109/allerton58177.2023.10313396"},"language":"en","primary_location":{"id":"doi:10.1109/allerton58177.2023.10313396","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton58177.2023.10313396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5041563197","display_name":"Akshay Mete","orcid":"https://orcid.org/0009-0009-9176-2265"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Akshay Mete","raw_affiliation_strings":["Texas A & M University,ECE Department,College Station,TX,USA"],"affiliations":[{"raw_affiliation_string":"Texas A & M University,ECE Department,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055489202","display_name":"Rahul Singh","orcid":"https://orcid.org/0000-0003-0363-3666"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rahul Singh","raw_affiliation_strings":["Indian Institute of Science,ECE Department,Bengaluru,India","ECE Department, Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,ECE Department,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"ECE Department, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101852131","display_name":"P. R. Kumar","orcid":"https://orcid.org/0000-0003-0474-080X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. R. Kumar","raw_affiliation_strings":["Texas A & M University,ECE Department,College Station,TX,USA"],"affiliations":[{"raw_affiliation_string":"Texas A & M University,ECE Department,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041563197"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20180133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7350194454193115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.609574556350708},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5645990371704102},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5380223989486694},{"id":"https://openalex.org/keywords/linear-quadratic-gaussian-control","display_name":"Linear-quadratic-Gaussian control","score":0.5164342522621155},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.49631577730178833},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4228097200393677},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4158082902431488},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3688536286354065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3609884977340698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2858288288116455},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28156474232673645},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22498762607574463}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7350194454193115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609574556350708},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5645990371704102},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5380223989486694},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.5164342522621155},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.49631577730178833},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4228097200393677},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4158082902431488},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3688536286354065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3609884977340698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2858288288116455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28156474232673645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22498762607574463},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton58177.2023.10313396","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton58177.2023.10313396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W105751747","https://openalex.org/W1583837637","https://openalex.org/W1972318568","https://openalex.org/W1974508877","https://openalex.org/W1982997797","https://openalex.org/W2004487554","https://openalex.org/W2009551863","https://openalex.org/W2048287263","https://openalex.org/W2069034916","https://openalex.org/W2094826322","https://openalex.org/W2097931172","https://openalex.org/W2106164082","https://openalex.org/W2115597380","https://openalex.org/W2123225686","https://openalex.org/W2168405694","https://openalex.org/W2753754162","https://openalex.org/W2765733960","https://openalex.org/W2914238450","https://openalex.org/W2963819344","https://openalex.org/W3015500735","https://openalex.org/W3015621283","https://openalex.org/W3020125231","https://openalex.org/W3124229194","https://openalex.org/W3173921152","https://openalex.org/W4206530644","https://openalex.org/W4206670532","https://openalex.org/W4224042014","https://openalex.org/W4225435134","https://openalex.org/W4225838216","https://openalex.org/W4234228486","https://openalex.org/W4236323066","https://openalex.org/W4244364296","https://openalex.org/W4248696375","https://openalex.org/W4250248097","https://openalex.org/W4287829052","https://openalex.org/W4378718336","https://openalex.org/W6602152948","https://openalex.org/W6629353124","https://openalex.org/W6639039794","https://openalex.org/W6640015871","https://openalex.org/W6657494743","https://openalex.org/W6675656252","https://openalex.org/W6684588631","https://openalex.org/W6686227676","https://openalex.org/W6736527823","https://openalex.org/W6743825324","https://openalex.org/W6763329203","https://openalex.org/W6764988152","https://openalex.org/W6774521036","https://openalex.org/W6785000746","https://openalex.org/W6785291173","https://openalex.org/W6810325554","https://openalex.org/W6810918382","https://openalex.org/W6840796770","https://openalex.org/W6853509183"],"related_works":["https://openalex.org/W1925875298","https://openalex.org/W4292701710","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W4400868993","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3096874164","https://openalex.org/W3182614517"],"abstract_inverted_index":{"The":[0],"exploration-exploitation":[1],"trade-off,":[2],"also":[3],"known":[4],"as":[5],"the":[6,11,24,44,88,92,104,114],"\"dual":[7],"control":[8],"problem\"":[9,14],"or":[10],"\"closed-loop":[12],"identifiability":[13],"is":[15],"a":[16,34,57],"fundamental":[17],"challenge":[18],"in":[19,56],"reinforcement":[20],"learning.":[21],"One":[22],"of":[23,32,59,91,100,108],"initial":[25],"approaches":[26],"proposed":[27],"for":[28,116],"this":[29],"problem":[30],"consisted":[31],"adding":[33],"bias":[35],"term":[36],"that":[37],"favored":[38],"models":[39],"with":[40,111],"larger":[41],"rewards":[42],"to":[43,52],"likelihood":[45],"function.":[46],"This":[47,95],"\"Reward-Biased\"":[48],"approach":[49],"was":[50],"shown":[51],"be":[53],"asymptotically":[54],"optimal":[55],"variety":[58],"contexts":[60],"including":[61],"Multi-Armed":[62],"Bandits":[63],"(MABs),":[64],"Markov":[65],"Decision":[66],"Processes":[67],"(MDPs),":[68],"Linear":[69],"Quadratic":[70],"Gaussian":[71],"(LQG)":[72],"systems,":[73,75],"nonlinear":[74],"and":[76,84,120],"controlled":[77],"diffusions.":[78],"Recent":[79],"results":[80],"on":[81,103,113],"regret":[82],"guarantees":[83],"empirical":[85],"experiments":[86],"highlight":[87],"performance":[89],"advantage":[90],"Reward-Biased":[93],"Method.":[94],"paper":[96],"provides":[97],"an":[98],"account":[99],"recent":[101],"developments":[102],"finite":[105],"time":[106],"analysis":[107],"RBMLE":[109],"along":[110],"insights":[112],"reason":[115],"its":[117],"competitive":[118],"advantage,":[119],"identifies":[121],"some":[122],"open":[123],"problems.":[124]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}