{"id":"https://openalex.org/W7163575715","doi":"https://doi.org/10.48550/arxiv.2606.05159","title":"X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation","display_name":"X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163575715","doi":"https://doi.org/10.48550/arxiv.2606.05159"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.05159","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05159","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.05159","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036233587","display_name":"Rachel Luo","orcid":"https://orcid.org/0000-0001-8296-4994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Rachel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137909057","display_name":"Michael Watson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Watson, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137866708","display_name":"Apoorva Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Apoorva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137841877","display_name":"Heng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Heng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137873591","display_name":"Han Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103887320","display_name":"Edward Schmerling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmerling, Edward","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088704174","display_name":"Sushant Veer","orcid":"https://orcid.org/0000-0003-3498-6448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veer, Sushant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091869385","display_name":"Boris Ivanovic","orcid":"https://orcid.org/0000-0002-8698-202X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivanovic, Boris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137905490","display_name":"Marco Pavone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavone, Marco","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":0.6565999984741211,"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":0.6565999984741211,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0786999985575676,"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":0.050999999046325684,"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/variance","display_name":"Variance (accounting)","score":0.6261000037193298},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.616599977016449},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4357999861240387},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.435699999332428},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3598000109195709},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.31279999017715454},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.3102000057697296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038000226020813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6389999985694885},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6017000079154968},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5133000016212463},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.05159","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05159","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":"doi:10.48550/arxiv.2606.05159","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05159","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4826059341430664}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rigorous":[0],"evaluation":[1,40],"of":[2,45,76,121,143,213],"learning-based":[3],"robotic":[4,215],"systems":[5],"is":[6,16,33,149],"an":[7],"essential":[8],"prerequisite":[9],"for":[10,80,99,113],"deployment.":[11],"However,":[12],"real-world":[13,77,115,144,176],"test":[14],"data":[15,27,47,55,65,203],"expensive":[17],"to":[18,186,207],"gather;":[19],"moreover,":[20],"in":[21,36,83,90,118],"a":[22,110,134,140,153],"typical":[23],"iterative":[24],"development":[25],"context,":[26],"gathered":[28],"from":[29,57,88,128],"the":[30,91,119,210],"latest":[31],"policy":[32,52],"necessarily":[34],"limited":[35],"scale.":[37],"This":[38],"motivates":[39],"methodologies":[41],"that":[42,200],"make":[43],"use":[44,98],"heterogeneous":[46,202],"sources,":[48],"including":[49],"simulation,":[50],"historical":[51],"logs,":[53],"and":[54,68,130,138,169,175,190],"collected":[56],"related":[58],"platforms":[59],"or":[60],"environments.":[61],"While":[62],"such":[63],"auxiliary":[64,131],"are":[66,71,163],"abundant":[67],"inexpensive,":[69],"they":[70],"generally":[72],"not":[73],"directly":[74],"representative":[75],"outcomes":[78],"--":[79,94],"example,":[81],"performance":[82,89,101],"simulation":[84],"may":[85],"differ":[86],"substantially":[87,208],"real":[92,129],"world":[93],"making":[95],"their":[96],"principled":[97],"high-confidence":[100],"estimation":[102,117],"challenging.":[103],"In":[104],"this":[105,146],"paper,":[106],"we":[107],"introduce":[108],"X4Val,":[109],"general":[111],"framework":[112],"variance-reduced":[114],"metric":[116],"presence":[120],"non-paired,":[122,201],"multi-domain":[123],"data.":[124],"X4Val":[125,183],"embeds":[126],"samples":[127,162],"domains":[132,180],"into":[133,152],"shared":[135],"representation":[136],"space":[137],"learns":[139],"transferable":[141],"predictor":[142,148],"metrics;":[145],"learned":[147],"then":[150],"incorporated":[151],"control-variates":[154],"estimator,":[155],"enabling":[156],"variance":[157,188],"reduction":[158,189],"even":[159],"when":[160],"paired":[161],"unavailable.":[164],"We":[165],"provide":[166],"theoretical":[167],"analysis":[168],"empirical":[170],"evaluations":[171],"on":[172],"autonomous":[173],"driving":[174],"robot":[177],"manipulation":[178],"tasks,":[179],"across":[181],"which":[182],"achieves":[184],"up":[185],"38.4%":[187],"demonstrates":[191],"consistent":[192],"improvements":[193],"over":[194],"strong":[195],"baselines.":[196],"These":[197],"results":[198],"show":[199],"can":[204],"be":[205],"leveraged":[206],"improve":[209],"sample":[211],"efficiency":[212],"rigorous":[214],"system":[216],"validation.":[217]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-05T00:00:00"}