{"id":"https://openalex.org/W3017362854","doi":null,"title":"Datasets for Data-Driven Reinforcement Learning","display_name":"Datasets for Data-Driven Reinforcement Learning","publication_year":2020,"publication_date":"2020-04-15","ids":{"openalex":"https://openalex.org/W3017362854","mag":"3017362854"},"language":"en","primary_location":{"id":"mag:3017362854","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.07219","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.07219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037720811","display_name":"Justin Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Justin Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102493293","display_name":"Aviral Kumar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aviral Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057773393","display_name":"Ofir Nachum","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ofir Nachum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048032272","display_name":"George Tucker","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Tucker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743","observed_orcids":["https://orcid.org/0000-0001-6764-2743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6764-2743","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":false,"cited_by_count":3,"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.8679999709129333},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.6930000185966492},{"id":"https://openalex.org/keywords/algorithm-evaluation","display_name":"algorithm evaluation","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8524895906448364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8517173528671265},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.835371732711792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.625082790851593},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5580090284347534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5578641295433044},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5059410929679871},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5027503967285156},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.48201170563697815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3657900094985962},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.19607198238372803},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3017362854","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.07219","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3017362854","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.07219","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1547105496","https://openalex.org/W1730555343","https://openalex.org/W2021151961","https://openalex.org/W2121863487","https://openalex.org/W2128812357","https://openalex.org/W2141559645","https://openalex.org/W2788026818","https://openalex.org/W2810785043","https://openalex.org/W2890192685","https://openalex.org/W2953981431"],"related_works":["https://openalex.org/W3016525976","https://openalex.org/W4402500861","https://openalex.org/W3037024314","https://openalex.org/W3101009114","https://openalex.org/W4360764815","https://openalex.org/W4393968337","https://openalex.org/W4360584316","https://openalex.org/W6910657599","https://openalex.org/W4380994509","https://openalex.org/W4221146510"],"abstract_inverted_index":{"The":[0],"offline":[1,59,63,77,92,105,206],"reinforcement":[2],"learning":[3],"(RL)":[4],"setting":[5,60],"(also":[6],"known":[7],"as":[8,23,193],"full":[9],"batch":[10],"RL),":[11],"where":[12,128],"a":[13,18,108,179,194,210],"policy":[14],"is":[15,21],"learned":[16],"from":[17],"static":[19],"dataset,":[20],"compelling":[22],"progress":[24,75,214],"enables":[25],"RL":[26,52,64,78,156,207],"methods":[27,208],"to":[28,68,80,101,201],"take":[29],"advantage":[30],"of":[31,40,98,104,114,143,164,182],"large,":[32],"previously-collected":[33],"datasets,":[34],"much":[35],"like":[36],"how":[37],"the":[38,58,91,135,199],"rise":[39],"large":[41],"datasets":[42,99,118,127,139,177],"has":[43],"fueled":[44],"results":[45],"in":[46,76,134,204,215],"supervised":[47],"learning.":[48],"However,":[49],"existing":[50,62,165,183,205],"online":[51],"benchmarks":[53,65,87],"are":[54,66],"not":[55],"tailored":[56],"towards":[57],"and":[61,123,138,151,161,176,188,209],"restricted":[67],"data":[69,152],"generated":[70,119],"by":[71,95,154],"partially-trained":[72,155],"agents,":[73,157],"making":[74],"difficult":[79],"measure.":[81],"In":[82],"this":[83,216],"work,":[84],"we":[85,158,170],"introduce":[86],"specifically":[88],"designed":[89],"for":[90,198,213],"setting,":[93],"guided":[94],"key":[96],"properties":[97,116],"relevant":[100],"real-world":[102],"applications":[103],"RL.":[106],"With":[107],"focus":[109],"on":[110],"dataset":[111],"collection,":[112],"examples":[113],"such":[115],"include:":[117],"via":[120],"hand-designed":[121],"controllers":[122],"human":[124],"demonstrators,":[125],"multitask":[126],"an":[129,185],"agent":[130],"performs":[131],"different":[132],"tasks":[133,150,175],"same":[136],"environment,":[137],"collected":[140,153],"with":[141,178],"mixtures":[142],"policies.":[144],"By":[145],"moving":[146],"beyond":[147],"simple":[148],"benchmark":[149,174],"reveal":[159],"important":[160],"unappreciated":[162],"deficiencies":[163],"algorithms.":[166],"To":[167],"facilitate":[168],"research,":[169],"have":[171],"released":[172],"our":[173],"comprehensive":[180],"evaluation":[181,186],"algorithms,":[184],"protocol,":[187],"open-source":[189],"examples.":[190],"This":[191],"serves":[192],"common":[195],"starting":[196],"point":[197],"community":[200],"identify":[202],"shortcomings":[203],"collaborative":[211],"route":[212],"emerging":[217],"area.":[218]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2020-04-24T00:00:00"}