{"id":"https://openalex.org/W2980603164","doi":"https://doi.org/10.1145/3366703","title":"Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces","display_name":"Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2980603164","doi":"https://doi.org/10.1145/3366703","mag":"2980603164"},"language":"en","primary_location":{"id":"doi:10.1145/3366703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3366703","source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3366703","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007393142","display_name":"Sean R. Sinclair","orcid":"https://orcid.org/0000-0002-7011-8253"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean R. Sinclair","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085889685","display_name":"Siddhartha Banerjee","orcid":"https://orcid.org/0000-0002-8954-4578"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Banerjee","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032294826","display_name":"Christina Lee Yu","orcid":"https://orcid.org/0000-0002-2165-5220"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christina Lee Yu","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":1.9615,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.86829159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"44"},"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":0.9993000030517578,"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":0.996999979019165,"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/discretization","display_name":"Discretization","score":0.7991443872451782},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7927860617637634},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6586928367614746},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5906274914741516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5460841059684753},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48687973618507385},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4794253706932068},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.44243842363357544},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4249642491340637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858043849468231},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3357691168785095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30959969758987427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24210834503173828}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7991443872451782},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7927860617637634},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6586928367614746},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5906274914741516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5460841059684753},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48687973618507385},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4794253706932068},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.44243842363357544},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4249642491340637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858043849468231},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3357691168785095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30959969758987427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24210834503173828},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3366703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3366703","source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1910.08151","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08151","pdf_url":"https://arxiv.org/pdf/1910.08151","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3366703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3366703","source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1513282676","display_name":"CAREER: Harnessing Prediction Engines and Non-Monetary Mechanisms for Real-Time Decision Making","funder_award_id":"1847393","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1558938383","display_name":null,"funder_award_id":"DMS-1839346","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4404219267","display_name":null,"funder_award_id":"W911NF-17-1-0094","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5446518243","display_name":null,"funder_award_id":"ECCS-1847393, DMS-1839346","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6051054619","display_name":"TRIPODS+X:RES: Collaborative Research: The Future of the Road - A Data-Driven Redesign of the Urban Transit Ecosystem","funder_award_id":"1839346","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980603164.pdf","grobid_xml":"https://content.openalex.org/works/W2980603164.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1483421714","https://openalex.org/W1701974503","https://openalex.org/W1747856733","https://openalex.org/W1850488217","https://openalex.org/W1976122053","https://openalex.org/W2032916024","https://openalex.org/W2049934117","https://openalex.org/W2071815241","https://openalex.org/W2103581319","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2122309512","https://openalex.org/W2132908009","https://openalex.org/W2148434045","https://openalex.org/W2334782222","https://openalex.org/W2546571074","https://openalex.org/W2911655748","https://openalex.org/W2911931139","https://openalex.org/W2913668833","https://openalex.org/W2941360707","https://openalex.org/W2941480181","https://openalex.org/W2943632322","https://openalex.org/W2944264312","https://openalex.org/W2946300093","https://openalex.org/W2950929549","https://openalex.org/W2951333509","https://openalex.org/W2956123884","https://openalex.org/W2963488874","https://openalex.org/W2963506504","https://openalex.org/W2963713569","https://openalex.org/W2964054583","https://openalex.org/W2966790463","https://openalex.org/W2985924367","https://openalex.org/W2990138404","https://openalex.org/W2990210896","https://openalex.org/W3011120880","https://openalex.org/W3201397603","https://openalex.org/W4205621617","https://openalex.org/W4297807520","https://openalex.org/W6682018617"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W4292701710","https://openalex.org/W2914522629"],"abstract_inverted_index":{"We":[0,56],"present":[1],"an":[2,98],"efficient":[3],"algorithm":[4,17,114],"for":[5,90],"model-free":[6],"episodic":[7],"reinforcement":[8],"learning":[9],"on":[10,20],"large":[11],"(potentially":[12],"continuous)":[13],"state-action":[14,40,92],"spaces.":[15],"Our":[16],"is":[18,32],"based":[19],"a":[21,35,106],"novel":[22],"Q-learning":[23,134],"policy":[24],"with":[25,135],"adaptive":[26,60],"data-driven":[27],"discretization.":[28,137],"The":[29],"central":[30],"idea":[31],"to":[33,105,117,131],"maintain":[34],"finer":[36],"partition":[37],"of":[38,64,67,87,121],"the":[39,65,68,72,77,84,118,122],"space":[41],"in":[42,48,125],"regions":[43],"which":[44,94],"are":[45],"frequently":[46],"visited":[47],"historical":[49],"trajectories,":[50],"and":[51,71,133],"have":[52],"higher":[53],"payoff":[54],"estimates.":[55],"demonstrate":[57,111],"how":[58,112],"our":[59,113],"partitions":[61],"take":[62],"advantage":[63],"shape":[66],"optimal":[69,99],"Q-function":[70],"joint":[73],"space,":[74],"without":[75],"sacrificing":[76],"worst-case":[78],"performance.":[79],"In":[80],"particular,":[81],"we":[82],"recover":[83],"regret":[85],"guarantees":[86],"prior":[88],"algorithms":[89],"continuous":[91],"spaces,":[93],"additionally":[95],"require":[96],"either":[97],"discretization":[100],"as":[101],"input,":[102],"and/or":[103],"access":[104],"simulation":[107],"oracle.":[108],"Moreover,":[109],"experiments":[110],"automatically":[115],"adapts":[116],"underlying":[119],"structure":[120],"problem,":[123],"resulting":[124],"much":[126],"better":[127],"performance":[128],"compared":[129],"both":[130],"heuristics":[132],"uniform":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}