{"id":"https://openalex.org/W4383109369","doi":"https://doi.org/10.1109/icra48891.2023.10161474","title":"Real World Offline Reinforcement Learning with Realistic Data Source","display_name":"Real World Offline Reinforcement Learning with Realistic Data Source","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109369","doi":"https://doi.org/10.1109/icra48891.2023.10161474"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161474","doi":"https://doi.org/10.1109/icra48891.2023.10161474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161474","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.06479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061988419","display_name":"Gaoyue Zhou","orcid":"https://orcid.org/0009-0002-1713-5086","observed_orcids":["https://orcid.org/0009-0002-1713-5086"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaoyue Zhou","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026314250","display_name":"Liyiming Ke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liyiming Ke","raw_affiliation_strings":["Work conducted durinu an internship at Meta AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Work conducted durinu an internship at Meta AI","institution_ids":[]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077719529","display_name":"Siddhartha S Srinivasa","orcid":"https://orcid.org/0000-0002-5091-106X","observed_orcids":["https://orcid.org/0000-0002-5091-106X"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Srinivasa","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761266","display_name":"Abhinav Gupta","orcid":"https://orcid.org/0000-0002-9197-0736","observed_orcids":["https://orcid.org/0000-0002-9197-0736","https://orcid.org/0000-0002-3646-2421"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Gupta","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732794","display_name":"Aravind Rajeswaran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Rajeswaran","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383672","display_name":"Vikash Kumar","orcid":"https://orcid.org/0000-0002-3168-7955","observed_orcids":["https://orcid.org/0000-0002-3168-7955"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikash Kumar","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9885,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9041639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7176","last_page":"7183"},"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/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/tabletop-manipulation","display_name":"tabletop manipulation","score":0.6589999794960022},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.7429999709129333},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.7580000162124634},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8709999918937683},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.7170000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869648933410645},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7453793287277222},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7008669972419739},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.670811116695404},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6590715646743774},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6287398338317871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6092362999916077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5524083375930786},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.506756603717804},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5051365494728088},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.49999165534973145},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.4622068405151367},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33873242139816284},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3156253695487976},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11727532744407654},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra48891.2023.10161474","doi":"https://doi.org/10.1109/icra48891.2023.10161474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161474","pdf_url":null,"source":{"id":"https://openalex.org/S4210217939","display_name":"Proceedings - IEEE International Conference on Robotics and Automation/Proceedings","issn_l":"1050-4729","issn":["1050-4729","2577-087X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.06479","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.06479","pdf_url":"https://arxiv.org/pdf/2210.06479","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.2210.06479","doi":"https://doi.org/10.48550/arxiv.2210.06479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.06479","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:2210.06479","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.06479","pdf_url":"https://arxiv.org/pdf/2210.06479","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/G3915411628","display_name":"NRI/Collaborative Research: Robot-Assisted Feeding: Towards Efficient, Safe, and Personalized Caregiving Robots","funder_award_id":"2132848","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4606971250","display_name":null,"funder_award_id":"2007011","funder_id":"https://openalex.org/F4320308578","funder_display_name":"Center for Hellenic Studies, Harvard University"},{"id":"https://openalex.org/G5389639558","display_name":"CHS: Small: Towards Usability in Robotic Assistance: A Formalism for Robot-Assisted Feeding while Adjusting to User Preferences","funder_award_id":"2007011","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/F4320308578","display_name":"Center for Hellenic Studies, Harvard University","ror":null},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"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/W4383109369.pdf","grobid_xml":"https://content.openalex.org/works/W4383109369.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2173248099","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2805805280","https://openalex.org/W2902907165","https://openalex.org/W2904453761","https://openalex.org/W2950624398","https://openalex.org/W2953981431","https://openalex.org/W2963669336","https://openalex.org/W2975999915","https://openalex.org/W2982316857","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3017367030","https://openalex.org/W3022566517","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034786558","https://openalex.org/W3037024314","https://openalex.org/W3037440645","https://openalex.org/W3048825312","https://openalex.org/W3097907450","https://openalex.org/W3101483449","https://openalex.org/W3101780148","https://openalex.org/W3106426955","https://openalex.org/W3108231325","https://openalex.org/W3112266718","https://openalex.org/W3115367651","https://openalex.org/W3127352841","https://openalex.org/W3130177876","https://openalex.org/W3154938165","https://openalex.org/W3156232699","https://openalex.org/W3167479696","https://openalex.org/W3169840145","https://openalex.org/W3171176697","https://openalex.org/W3173845672","https://openalex.org/W3185189976","https://openalex.org/W3187722890","https://openalex.org/W3197820606","https://openalex.org/W3199265017","https://openalex.org/W3200159855","https://openalex.org/W3203511201","https://openalex.org/W3205794883","https://openalex.org/W3206464427","https://openalex.org/W3206827162","https://openalex.org/W3207091059","https://openalex.org/W3212637808","https://openalex.org/W3214251933","https://openalex.org/W3214599998","https://openalex.org/W4221146510","https://openalex.org/W4221159977","https://openalex.org/W4223423875","https://openalex.org/W6684338915","https://openalex.org/W6741002519","https://openalex.org/W6776601253","https://openalex.org/W6799150178","https://openalex.org/W6802525821","https://openalex.org/W6810080435","https://openalex.org/W6960125083","https://openalex.org/W7133210602"],"related_works":["https://openalex.org/W4385438620","https://openalex.org/W4385890203","https://openalex.org/W4402500861","https://openalex.org/W4402353773","https://openalex.org/W7070636510","https://openalex.org/W6910657599","https://openalex.org/W7220830350","https://openalex.org/W4388835885","https://openalex.org/W2980825073","https://openalex.org/W3199265017"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,9,119],"(ORL)":[3],"holds":[4],"great":[5],"promise":[6],"for":[7,48,72],"robot":[8,74,88],"due":[10],"to":[11,14],"its":[12],"ability":[13],"learn":[15],"from":[16,60,130],"arbitrary":[17],"pre-generated":[18],"experience.":[19],"However,":[20],"current":[21],"ORL":[22,104,116,126],"benchmarks":[23],"are":[24,67],"almost":[25],"entirely":[26],"in":[27],"simulation":[28],"and":[29,43,90,99,117,124,136,144],"utilize":[30],"contrived":[31],"datasets":[32],"like":[33],"replay":[34],"buffers":[35],"of":[36,63,102],"online":[37],"RL":[38],"agents":[39],"or":[40],"sub-optimal":[41],"trajectories,":[42],"thus":[44],"hold":[45],"limited":[46],"relevance":[47],"real-world":[49,73,108],"robotics.":[50],"In":[51],"this":[52],"work":[53],"(Real-ORL),":[54],"we":[55,79],"posit":[56],"that":[57,115,125],"data":[58,70,134],"collected":[59,85],"safe":[61],"operations":[62],"closely":[64],"related":[65],"tasks":[66],"more":[68],"practical":[69],"sources":[71,135],"learning.":[75,139],"Under":[76],"these":[77],"settings,":[78],"perform":[80],"an":[81],"extensive":[82],"(6500+":[83],"trajectories":[84],"over":[86],"800+":[87],"hours":[89],"270+":[91],"human":[92],"labor":[93],"hour)":[94],"empirical":[95],"study":[96,113],"evaluating":[97],"generalization":[98],"transfer":[100],"capabilities":[101],"representative":[103],"methods":[105],"on":[106],"four":[107],"tabletop":[109],"manipulation":[110],"tasks.":[111],"Our":[112],"finds":[114],"imitation":[118,138],"prefer":[120],"different":[121],"action":[122],"spaces,":[123],"algorithms":[127],"can":[128],"generalize":[129],"leveraging":[131],"offline":[132],"heterogeneous":[133],"outperform":[137],"We":[140],"release":[141],"our":[142],"dataset":[143],"implementations":[145],"at":[146],"URL:":[147],"https://sites.google.com/view/real-orl.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-07-05T00:00:00"}