{"id":"https://openalex.org/W4304701371","doi":"https://doi.org/10.48550/arxiv.2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","display_name":"The Role of Coverage in Online Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4304701371","doi":"https://doi.org/10.48550/arxiv.2210.04157"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.04157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04157","pdf_url":"https://arxiv.org/pdf/2210.04157","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.04157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061481788","display_name":"Tengyang Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tengyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075069827","display_name":"Dylan J. Foster","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Foster, Dylan J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405525","display_name":"Yu Bai","orcid":"https://orcid.org/0009-0003-9012-6327","observed_orcids":["https://orcid.org/0009-0003-9012-6327"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033815877","display_name":"Nan Jiang","orcid":"https://orcid.org/0000-0002-4570-180X","observed_orcids":["https://orcid.org/0000-0002-4570-180X","https://orcid.org/0000-0003-2709-840X","https://orcid.org/0009-0001-4625-4554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108381794","display_name":"Sham M. Kakade","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kakade, Sham M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00019999999494757503,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/online-reinforcement-learning","display_name":"online reinforcement learning","score":0.9139999747276306},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.718999981880188},{"id":"https://openalex.org/keywords/coverability","display_name":"coverability","score":0.7689999938011169},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7490000128746033}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8518862724304199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.688323974609375},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6276949644088745},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.6011059284210205},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5255283713340759},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5140424966812134},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4950973093509674},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.44374144077301025},{"id":"https://openalex.org/C119322782","wikidata":"https://www.wikidata.org/wiki/Q2662236","display_name":"VC dimension","level":2,"score":0.4304007887840271},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.426453173160553},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38634192943573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35275834798812866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24219340085983276},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.04157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04157","pdf_url":"https://arxiv.org/pdf/2210.04157","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2210.04157","doi":"https://doi.org/10.48550/arxiv.2210.04157","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.04157","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.04157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04157","pdf_url":"https://arxiv.org/pdf/2210.04157","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1034401897","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1427281996","display_name":"AF: Medium: Collaborative Research: Estimation, Learning, and Memory: The Quest for Statistically Optimal Algorithms","funder_award_id":"1703574","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2186497367","display_name":"AI Institute for Future Edge Networks and Distributed Intelligence (AI-EDGE)","funder_award_id":"2112471","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4720003262","display_name":null,"funder_award_id":"N00014-22","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304701371.pdf","grobid_xml":"https://content.openalex.org/works/W4304701371.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2173248099","https://openalex.org/W2614208603","https://openalex.org/W2970355847","https://openalex.org/W4225838216","https://openalex.org/W4281734993","https://openalex.org/W4286233210","https://openalex.org/W7133197582","https://openalex.org/W7133244585"],"related_works":["https://openalex.org/W4367060976","https://openalex.org/W4377864600","https://openalex.org/W4392736086","https://openalex.org/W4313303709","https://openalex.org/W3215067404","https://openalex.org/W4415181767","https://openalex.org/W4382173275","https://openalex.org/W7128771689","https://openalex.org/W4226283576","https://openalex.org/W4391046029"],"abstract_inverted_index":{"Coverage":[0],"conditions":[1,31],"--":[2,15,49,52,74,90],"which":[3],"assert":[4],"that":[5,53,72,75,82,127,147],"the":[6,12,22,54,99,114,171],"data":[7,59,80],"logging":[8],"distribution":[9,60,81],"adequately":[10],"covers":[11],"state":[13],"space":[14],"play":[16],"a":[17,44,58,79,84,95,167,177],"fundamental":[18],"role":[19],"in":[20],"determining":[21],"sample":[23],"complexity":[24,149,169],"of":[25,57,78,98,131],"offline":[26,137],"reinforcement":[27,37],"learning.":[28],"While":[29],"such":[30],"might":[32],"seem":[33],"irrelevant":[34],"to":[35,161,175],"online":[36,67,142,152],"learning":[38],"at":[39],"first":[40],"glance,":[41],"we":[42,70],"establish":[43],"new":[45,168],"connection":[46],"by":[47,106,125],"showing":[48],"somewhat":[50],"surprisingly":[51],"mere":[55],"existence":[56,77],"with":[61],"good":[62],"coverage":[63,86],"can":[64,91,103],"enable":[65],"sample-efficient":[66,110],"RL.":[68,143],"Concretely,":[69],"show":[71,146],"coverability":[73],"is,":[76],"satisfies":[83],"ubiquitous":[85],"condition":[87],"called":[88],"concentrability":[89],"be":[92,104],"viewed":[93],"as":[94],"structural":[96],"property":[97],"underlying":[100],"MDP,":[101],"and":[102,157,165],"exploited":[105],"standard":[107],"algorithms":[108],"for":[109,136,141,151],"exploration,":[111],"even":[112],"when":[113],"agent":[115],"does":[116],"not":[117],"know":[118],"said":[119],"distribution.":[120],"We":[121,144],"complement":[122],"this":[123],"result":[124],"proving":[126],"several":[128],"weaker":[129],"notions":[130],"coverage,":[132],"despite":[133],"being":[134],"sufficient":[135],"RL,":[138,153],"are":[139],"insufficient":[140],"also":[145],"existing":[148],"measures":[150],"including":[154],"Bellman":[155],"rank":[156],"Bellman-Eluder":[158],"dimension,":[159],"fail":[160],"optimally":[162],"capture":[163],"coverability,":[164],"propose":[166],"measure,":[170],"sequential":[172],"extrapolation":[173],"coefficient,":[174],"provide":[176],"unification.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-10-12T00:00:00"}