{"id":"https://openalex.org/W4293575545","doi":"https://doi.org/10.48550/arxiv.2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","display_name":"Light-weight probing of unsupervised representations for Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-25","ids":{"openalex":"https://openalex.org/W4293575545","doi":"https://doi.org/10.48550/arxiv.2208.12345"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2208.12345","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.12345","pdf_url":"https://arxiv.org/pdf/2208.12345","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/2208.12345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118983622","display_name":"Wancong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Wancong","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035393546","display_name":"Anthony GX-Chen","orcid":"https://orcid.org/0000-0003-4607-8682","observed_orcids":["https://orcid.org/0000-0003-4607-8682"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"GX-Chen, Anthony","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015115393","display_name":"Vlad Sobal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sobal, Vlad","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":"https://orcid.org/0000-0002-1992-2684","observed_orcids":["https://orcid.org/0000-0002-1992-2684"]},"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"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LeCun, Yann","raw_affiliation_strings":["Facebook AI Research","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029981206","display_name":"Nicolas Carion","orcid":"https://orcid.org/0000-0002-2308-9680","observed_orcids":["https://orcid.org/0000-0002-2308-9680"]},"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"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carion, Nicolas","raw_affiliation_strings":["Facebook AI Research","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/T11574","display_name":"Artificial Intelligence in Games","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/reinforcement-learning","display_name":"reinforcement learning","score":0.7549999952316284},{"id":"https://openalex.org/keywords/linear-probing","display_name":"linear probing","score":0.9869999885559082},{"id":"https://openalex.org/keywords/forward-model","display_name":"forward model","score":0.9120000004768372}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8179780840873718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78867506980896},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7293996810913086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6919423341751099},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6866227388381958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6634813547134399},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6552782654762268},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.508003294467926},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46099427342414856},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2208.12345","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.12345","pdf_url":"https://arxiv.org/pdf/2208.12345","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.2208.12345","doi":"https://doi.org/10.48550/arxiv.2208.12345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.12345","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:2208.12345","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.12345","pdf_url":"https://arxiv.org/pdf/2208.12345","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293575545.pdf","grobid_xml":"https://content.openalex.org/works/W4293575545.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3132674603","https://openalex.org/W7062670630","https://openalex.org/W4293567721","https://openalex.org/W4297437615","https://openalex.org/W4380353729","https://openalex.org/W7128822371","https://openalex.org/W3011264688","https://openalex.org/W4293545723","https://openalex.org/W3106426587","https://openalex.org/W3211095199"],"abstract_inverted_index":{"Unsupervised":[0],"visual":[1,17,188],"representation":[2],"learning":[3,26,172],"offers":[4],"the":[5,22,31,51,66,76,84,109,117,122,144,155,178,181,184,187,191,195],"opportunity":[6],"to":[7,14,99,131,157],"leverage":[8],"large":[9],"corpora":[10],"of":[11,24,33,68,86,94,146,180,186,194],"unlabeled":[12],"trajectories":[13],"form":[15],"useful":[16],"representations,":[18],"which":[19,40,95],"can":[20,59],"benefit":[21],"training":[23,37],"reinforcement":[25],"(RL)":[27],"algorithms.":[28],"However,":[29],"evaluating":[30],"fitness":[32],"such":[34],"representations":[35],"requires":[36],"RL":[38,70,101,119,159],"algorithms":[39,148],"is":[41],"computationally":[42],"intensive":[43],"and":[44,83,129,149,190],"has":[45],"high":[46],"variance":[47,128],"outcomes.":[48],"Inspired":[49],"by":[50],"vision":[52],"community,":[53],"we":[54,73,106,167],"study":[55],"whether":[56],"linear":[57],"probing":[58,110],"be":[60],"a":[61,80,90,138],"proxy":[62],"evaluation":[63],"task":[64],"for":[65,75,142,161,175],"quality":[67],"unsupervised":[69,196],"representation.":[71],"Specifically,":[72],"probe":[74],"observed":[77],"reward":[78],"in":[79,89],"given":[81,91],"state":[82],"action":[85],"an":[87],"expert":[88],"state,":[92],"both":[93],"are":[96,112],"generally":[97],"applicable":[98],"many":[100],"domains.":[102],"Through":[103],"rigorous":[104],"experimentation,":[105],"show":[107],"that":[108],"tasks":[111],"strongly":[113],"rank":[114],"correlated":[115],"with":[116],"downstream":[118],"performance":[120],"on":[121],"Atari100k":[123],"Benchmark,":[124],"while":[125],"having":[126],"lower":[127,133],"up":[130],"600x":[132],"computational":[134],"cost.":[135],"This":[136],"provides":[137],"more":[139],"efficient":[140],"method":[141],"exploring":[143],"space":[145],"pretraining":[147,152],"identifying":[150],"promising":[151],"recipes":[153,174],"without":[154],"need":[156],"run":[158],"evaluations":[160],"every":[162],"setting.":[163],"Leveraging":[164],"this":[165],"framework,":[166],"further":[168],"improve":[169],"existing":[170],"self-supervised":[171],"(SSL)":[173],"RL,":[176],"highlighting":[177],"importance":[179],"forward":[182],"model,":[183],"size":[185],"backbone,":[189],"precise":[192],"formulation":[193],"objective.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-08-30T00:00:00"}