{"id":"https://openalex.org/W7138113682","doi":"https://doi.org/10.1609/aaai.v40i27.39412","title":"Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning","display_name":"Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138113682","doi":"https://doi.org/10.1609/aaai.v40i27.39412"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i27.39412","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39412","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39412/43373","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39412/43373","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129697389","display_name":"Avik Kar","orcid":null},"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":true,"raw_author_name":"Avik Kar","raw_affiliation_strings":["Indian Institute of Science"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129704290","display_name":"Rahul Singh","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5129697389"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35353535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"27","first_page":"22527","last_page":"22535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.7843000292778015,"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":0.7843000292778015,"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":0.18709999322891235,"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/T13553","display_name":"Age of Information Optimization","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8870999813079834},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7627999782562256},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.722000002861023},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6632999777793884},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5651999711990356},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.5605999827384949},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5019000172615051},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4122999906539917}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8870999813079834},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7627999782562256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.722000002861023},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5651999711990356},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.545199990272522},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4447999894618988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44350001215934753},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.375},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3165000081062317},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i27.39412","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39412","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39412/43373","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i27.39412","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39412","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39412/43373","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.747514545917511,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138113682.pdf","grobid_xml":"https://content.openalex.org/works/W7138113682.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,49],"study":[1],"infinite-horizon":[2],"average-reward":[3],"reinforcement":[4],"learning":[5],"for":[6,63,75,186],"continuous":[7],"space":[8,33,170],"Lipschitz":[9],"Markov":[10],"decision":[11],"processes":[12],"(MDPs)":[13],"in":[14,46,131,201],"which":[15],"an":[16,103],"agent":[17,140],"can":[18],"play":[19],"policies":[20,99],"from":[21],"a":[22,96,143,148,189],"given":[23,95],"set":[24,97],"\u03a6.":[25,100,123],"The":[26],"proposed":[27,126],"algorithms":[28,127],"efficiently":[29],"explore":[30],"the":[31,37,47,52,83,86,92,107,110,116,125,133,139,154,166,193,202],"policy":[32,158],"by":[34],"\u201czooming\u201d":[35],"into":[36],"\u201cpromising":[38],"regions\u201d":[39],"of":[40,85,98,106,109,156,168],"\u03a6,":[41],"thereby":[42],"achieving":[43],"adaptivity":[44],"gains":[45],"performance.":[48],"upper":[50],"bound":[51],"regret":[53,130,185],"as":[54,119,121,165],"O":[55,183],"\u0303(T^(1-d_(eff.)^(-1)":[56],")":[57],"),":[58],"where":[59],"d_(eff.)":[60,69,163,178],"=":[61,70,179],"d_z^\u03a6+2":[62],"our":[64,76],"model-free":[65],"algorithm":[66,78],"PZRL-MF":[67],"and":[68,89,112,175],"2d_S":[71],"+":[72],"d_z^\u03a6+":[73],"3":[74],"model-based":[77],"PZRL-MB.":[79],"Here,":[80],"d_S":[81],"is":[82,91,102,136,198],"dimension":[84,94,167],"state":[87],"space,":[88,159],"d_z^\u03a6":[90,101],"zooming":[93],"alternative":[104],"measure":[105],"complexity":[108],"problem,":[111],"it":[113],"depends":[114],"on":[115,122,192],"underlying":[117],"MDP":[118],"well":[120],"Hence,":[124],"exhibit":[128],"low":[129],"case":[132,155],"problem":[134],"instance":[135],"benign":[137],"and/or":[138],"competes":[141],"against":[142],"low-complexity":[144],"\u03a6":[145],"(that":[146],"has":[147],"small":[149],"d_z^\u03a6).":[150],"When":[151],"specialized":[152],"to":[153],"finite-dimensional":[157],"we":[160],"obtain":[161,177],"that":[162,197],"scales":[164],"this":[169],"under":[171,188],"mild":[172],"technical":[173],"conditions;":[174],"also":[176],"2,":[180],"or":[181],"equivalently":[182],"\u0303(\u221aT)":[184],"PZRL-MF,":[187],"curvature":[190],"condition":[191],"average":[194],"reward":[195],"function":[196],"commonly":[199],"used":[200],"multi-armed":[203],"bandit":[204],"(MAB)":[205],"literature.":[206]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}