{"id":"https://openalex.org/W4404308578","doi":"https://doi.org/10.48550/arxiv.2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","display_name":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4404308578","doi":"https://doi.org/10.48550/arxiv.2410.18076"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.18076","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18076","pdf_url":"https://arxiv.org/pdf/2410.18076","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.18076","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106018507","display_name":"Max Wilcoxson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilcoxson, Max","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069290071","display_name":"Qiyang Li","orcid":"https://orcid.org/0000-0003-2214-9968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053366330","display_name":"Kevin Frans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frans, Kevin","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"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levine, Sergey","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":0,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9799000024795532,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9799000024795532,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9714000225067139,"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"}},{"id":"https://openalex.org/T12171","display_name":"Open Education and E-Learning","score":0.9333999752998352,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/computer-science","display_name":"Computer science","score":0.5159140825271606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.342308908700943},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3259849548339844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32140278816223145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5159140825271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.342308908700943},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3259849548339844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32140278816223145}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.18076","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18076","pdf_url":"https://arxiv.org/pdf/2410.18076","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"},{"id":"doi:10.48550/arxiv.2410.18076","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.18076","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.18076","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18076","pdf_url":"https://arxiv.org/pdf/2410.18076","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3484629716","display_name":null,"funder_award_id":"FA9550-22-1-0273","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4528395542","display_name":null,"funder_award_id":"N00014-22-1-2773","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"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/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"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/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404308578.pdf","grobid_xml":"https://content.openalex.org/works/W4404308578.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Unsupervised":[0],"pretraining":[1],"has":[2,80],"been":[3,81],"transformative":[4],"in":[5,21],"many":[6],"supervised":[7],"domains.":[8],"However,":[9],"applying":[10],"such":[11],"ideas":[12,87,109],"to":[13,53,64,84,160,170],"reinforcement":[14],"learning":[15],"(RL)":[16],"presents":[17],"a":[18,66,104,120,162,182],"unique":[19],"challenge":[20],"that":[22,103,143,165],"fine-tuning":[23],"does":[24],"not":[25],"involve":[26],"mimicking":[27],"task-specific":[28],"data,":[29],"but":[30],"rather":[31],"exploring":[32],"and":[33,124,132],"locating":[34],"the":[35],"solution":[36],"through":[37],"iterative":[38],"self-improvement.":[39],"In":[40,173],"this":[41],"work,":[42],"we":[43],"study":[44],"how":[45,83],"unlabeled":[46,127],"offline":[47],"trajectory":[48],"data":[49,60,75,99,138,156],"can":[50,61],"be":[51,62],"leveraged":[52],"learn":[54,161],"efficient":[55],"exploration":[56],"strategies.":[57],"While":[58],"prior":[59,137,179],"used":[63],"pretrain":[65],"set":[67],"of":[68,107,184],"low-level":[69,117,168],"skills,":[70],"or":[71],"as":[72,153],"additional":[73,154],"off-policy":[74,155],"for":[76,89,100,157],"online":[77,90,158],"RL,":[78],"it":[79],"unclear":[82],"combine":[85],"these":[86,108,150],"effectively":[88],"exploration.":[91],"Our":[92,113],"method":[93,114],"SUPE":[94,148,176],"(Skills":[95],"from":[96],"Unlabeled":[97],"Prior":[98],"Exploration)":[101],"demonstrates":[102],"careful":[105],"combination":[106],"compounds":[110],"their":[111],"benefits.":[112],"first":[115],"extracts":[116],"skills":[118,169],"using":[119],"variational":[121],"autoencoder":[122],"(VAE),":[123],"then":[125],"pseudo-labels":[126],"trajectories":[128],"with":[129],"optimistic":[130],"rewards":[131],"high-level":[133,163],"action":[134],"labels,":[135],"transforming":[136],"into":[139],"high-level,":[140],"task-relevant":[141],"examples":[142,152],"encourage":[144],"novelty-seeking":[145],"behavior.":[146],"Finally,":[147],"uses":[149],"transformed":[151],"RL":[159],"policy":[164],"composes":[166],"pretrained":[167],"explore":[171],"efficiently.":[172],"our":[174],"experiments,":[175],"consistently":[177],"outperforms":[178],"strategies":[180],"across":[181],"suite":[183],"42":[185],"long-horizon,":[186],"sparse-reward":[187],"tasks.":[188],"Code:":[189],"https://github.com/rail-berkeley/supe.":[190]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}