{"id":"https://openalex.org/W4413680290","doi":"https://doi.org/10.23919/wiopt66569.2025.11123313","title":"Tabular and Deep Reinforcement Learning for Gittins Index","display_name":"Tabular and Deep Reinforcement Learning for Gittins Index","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4413680290","doi":"https://doi.org/10.23919/wiopt66569.2025.11123313"},"language":"en","primary_location":{"id":"doi:10.23919/wiopt66569.2025.11123313","is_oa":false,"landing_page_url":"https://doi.org/10.23919/wiopt66569.2025.11123313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 23rd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)","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/A5093760398","display_name":"Harshit Dhankhar","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Harshit Dhankhar","raw_affiliation_strings":["IIT Patna,Department of Mathematics,Patna,India"],"affiliations":[{"raw_affiliation_string":"IIT Patna,Department of Mathematics,Patna,India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044012386","display_name":"Kshitij Mishra","orcid":"https://orcid.org/0000-0001-6474-2757"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kshitij Mishra","raw_affiliation_strings":["Computer Systems Group, IIIT Hyderabad,Hyderabad,Telegana"],"affiliations":[{"raw_affiliation_string":"Computer Systems Group, IIIT Hyderabad,Hyderabad,Telegana","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094780541","display_name":"Tejas Bodas","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tejas Bodas","raw_affiliation_strings":["Computer Systems Group, IIIT Hyderabad,Hyderabad,Telegana"],"affiliations":[{"raw_affiliation_string":"Computer Systems Group, IIIT Hyderabad,Hyderabad,Telegana","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093760398"],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27638223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.4296000003814697,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.4296000003814697,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7919295430183411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6970884203910828},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6395761966705322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5571592450141907},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12666621804237366}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7919295430183411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970884203910828},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6395761966705322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571592450141907},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12666621804237366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/wiopt66569.2025.11123313","is_oa":false,"landing_page_url":"https://doi.org/10.23919/wiopt66569.2025.11123313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 23rd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)","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":28,"referenced_works":["https://openalex.org/W146031494","https://openalex.org/W166250193","https://openalex.org/W2044502527","https://openalex.org/W2056921512","https://openalex.org/W2109643282","https://openalex.org/W2140519736","https://openalex.org/W2145339207","https://openalex.org/W2154204727","https://openalex.org/W2159471113","https://openalex.org/W2499002200","https://openalex.org/W2511028367","https://openalex.org/W2902806543","https://openalex.org/W2970029779","https://openalex.org/W2973229164","https://openalex.org/W3022217175","https://openalex.org/W3125634603","https://openalex.org/W3165083159","https://openalex.org/W4206129830","https://openalex.org/W4206530644","https://openalex.org/W4255654664","https://openalex.org/W4297580360","https://openalex.org/W4313648241","https://openalex.org/W4377148696","https://openalex.org/W4386422234","https://openalex.org/W4388740203","https://openalex.org/W4391410851","https://openalex.org/W4391925936","https://openalex.org/W4402785288"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"In":[0,29,74],"the":[1,7,18,26,34,43,60,71,88,95,99,111,142,171,178],"realm":[2],"of":[3,173],"multi-armed":[4,100],"bandit":[5,101],"problems,":[6],"Gittins":[8,44,89,112,143],"index":[9,90],"policy":[10],"is":[11,158],"known":[12],"to":[13,53,63,69,141,162],"be":[14,47],"optimal":[15],"in":[16,128,134,176,181,190],"maximizing":[17],"expected":[19],"total":[20],"discounted":[21],"reward":[22,72],"obtained":[23],"from":[24],"pulling":[25],"Markovian":[27,35],"arms.":[28],"most":[30],"realistic":[31],"scenarios":[32],"however,":[33],"state":[36,61,155],"transition":[37],"probabilities":[38],"are":[39,92,188],"unknown":[40,195],"and":[41,81,130,136,157,192],"therefore":[42],"indices":[45,66],"cannot":[46],"computed.":[48],"One":[49],"can":[50],"then":[51],"resort":[52],"reinforcement":[54],"learning":[55,87],"(RL)":[56],"algorithms":[57,85,108,115,175],"that":[58,91,109],"explore":[59],"space":[62,124],"learn":[64,110],"these":[65],"while":[67],"exploiting":[68],"maximize":[70],"collected.":[73],"this":[75],"work,":[76],"we":[77,169],"propose":[78],"tabular":[79],"(QGI)":[80],"Deep":[82],"RL":[83,107],"(DGN)":[84],"for":[86,98,151],"based":[93],"on":[94],"retirement":[96],"formulation":[97],"problem.":[102],"When":[103],"compared":[104],"with":[105,153],"existing":[106,163],"index,":[113],"our":[114,147,174],"have":[116,193],"a":[117,159,166,182],"lower":[118],"run":[119],"time,":[120],"require":[121],"less":[122],"storage":[123],"(small":[125],"Q-table":[126],"size":[127],"QGI":[129],"smaller":[131],"replay":[132],"buffer":[133],"DGN),":[135],"illustrate":[137],"better":[138],"empirical":[139],"convergence":[140],"index.":[144],"This":[145],"makes":[146],"algorithm":[148],"well":[149],"suited":[150],"problems":[152],"large":[154],"spaces":[156],"viable":[160],"alternative":[161],"methods.":[164],"As":[165],"key":[167],"application,":[168],"demonstrate":[170],"use":[172],"minimizing":[177],"mean":[179],"flowtime":[180],"job":[183],"scheduling":[184],"problem":[185],"when":[186],"jobs":[187],"available":[189],"batches":[191],"an":[194],"service":[196],"time":[197],"distribution.":[198]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}