{"id":"https://openalex.org/W7225265204","doi":"https://doi.org/10.48550/arxiv.2611.05368","title":"GUILD: Guided Iterative Data Collection for Imitation Learning","display_name":"GUILD: Guided Iterative Data Collection for Imitation Learning","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225265204","doi":"https://doi.org/10.48550/arxiv.2611.05368"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.05368","doi":"https://doi.org/10.48550/arxiv.2611.05368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05368","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.05368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076417053","display_name":"Shivin Dass","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dass, Shivin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134760728","display_name":"Kevin Nguyen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160720625","display_name":"Rohan Yelandur","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yelandur, Rohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786021","display_name":"Junhong Xu","orcid":"https://orcid.org/0000-0001-7127-5093","observed_orcids":["https://orcid.org/0000-0001-7127-5093"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Junhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065655761","display_name":"Roberto Mart\u00edn-Mart\u00edn","orcid":"https://orcid.org/0000-0002-9586-2759","observed_orcids":["https://orcid.org/0000-0002-9586-2759"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00edn-Mart\u00edn, Roberto","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":false,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922000169754028,"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":0.9922000169754028,"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":0.007199999876320362,"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":9.999999747378752e-05,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954999804496765},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7486000061035156},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.7167999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5333999991416931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C2778949103","wikidata":"https://www.wikidata.org/wiki/Q600717","display_name":"Staring","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3450999855995178},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.05368","doi":"https://doi.org/10.48550/arxiv.2611.05368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05368","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.05368","doi":"https://doi.org/10.48550/arxiv.2611.05368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05368","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning":[1],"policies":[2],"in":[3,26,192],"robotics":[4],"are":[5],"trained":[6],"on":[7,21,166],"datasets":[8,43,56],"collected":[9,90,161],"through":[10],"costly":[11],"real-world":[12],"teleoperation.":[13],"Often,":[14],"the":[15,22,64,116,160,184],"data-collection":[16],"process":[17],"is":[18,173],"unguided,":[19],"relying":[20],"teleoperator's":[23],"intuition,":[24],"resulting":[25],"data":[27,87,108,112,137,150,155,181,185,201,213],"that":[28,39,82,101,199],"contributes":[29],"little":[30],"to":[31,91,114,128,178,211],"overall":[32],"policy":[33,47,94,146,164],"performance.":[34,95],"Recent":[35],"work":[36],"has":[37],"shown":[38],"curating":[40],"such":[41],"unguided":[42],"can":[44],"substantially":[45,203],"improve":[46],"performance,":[48],"but":[49],"these":[50],"approaches":[51],"operate":[52],"by":[53],"filtering":[54],"existing":[55],"after":[57],"collection":[58,109,186,202,214],"and":[59,107,110,134,194,207,218],"therefore":[60],"do":[61],"not":[62,144],"prevent":[63],"acquisition":[65],"of":[66],"uninformative":[67],"data.":[68],"In":[69],"this":[70],"work,":[71],"we":[72,121,148,157],"propose":[73],"GUILD,":[74],"a":[75,167],"novel":[76],"Guided":[77],"Data":[78],"Collection":[79],"(GDC)":[80],"method":[81],"actively":[83],"reasons":[84],"about":[85],"which":[86],"should":[88],"be":[89],"maximize":[92],"downstream":[93],"We":[96,188],"introduce":[97],"an":[98],"iterative":[99],"framework":[100],"alternates":[102],"between":[103],"1)":[104],"task":[105,119],"proposal":[106],"2)":[111],"evaluation":[113],"close":[115],"loop.":[117,187],"For":[118],"proposal,":[120],"leverage":[122],"semantic":[123,141],"priors":[124],"from":[125],"vision-language":[126],"models":[127],"identify":[129],"relevant":[130],"environments,":[131],"object":[132],"configurations,":[133],"goals":[135],"for":[136],"collection.":[138],"However,":[139],"since":[140],"relevance":[142],"does":[143],"imply":[145],"improvement,":[147],"perform":[149],"evaluation.":[151],"By":[152],"leveraging":[153],"predictive":[154],"attribution":[156],"approximate":[158],"how":[159],"trajectories":[162],"influence":[163],"performance":[165,209],"target":[168],"deployment":[169,208],"setting.":[170],"This":[171],"signal":[172],"then":[174],"used":[175],"as":[176],"feedback":[177],"guide":[179],"subsequent":[180],"collection,":[182],"closing":[183],"evaluate":[189],"our":[190],"approach":[191],"simulation":[193],"real":[195],"robot":[196],"settings,":[197],"demonstrating":[198],"guided":[200],"improves":[204],"sample":[205],"efficiency":[206],"compared":[210],"passive":[212],"strategies,":[215],"multiple":[216],"baselines":[217],"experienced":[219],"roboticists.":[220],"More":[221],"information":[222],"at":[223],"https://robin-lab.cs.utexas.edu/guild2026/":[224]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-05T00:00:00"}