{"id":"https://openalex.org/W7223845342","doi":"https://doi.org/10.48550/arxiv.2610.34035","title":"Prior-Data Fitted Networks for In-Context Off-Policy Evaluation","display_name":"Prior-Data Fitted Networks for In-Context Off-Policy Evaluation","publication_year":2026,"publication_date":"2026-10-25","ids":{"openalex":"https://openalex.org/W7223845342","doi":"https://doi.org/10.48550/arxiv.2610.34035"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.34035","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.34035","pdf_url":"https://arxiv.org/pdf/2610.34035","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/2610.34035","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137089269","display_name":"Shuguang Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu, Shuguang","raw_affiliation_strings":["The Hong Kong Polytechnic University , Hong Kong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University , Hong Kong , China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159900047","display_name":"Ting Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ting","raw_affiliation_strings":["Shanghai University of Finance and Economics , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics , Shanghai , China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159841316","display_name":"Fan Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Fan","raw_affiliation_strings":["Shanghai University of Finance and Economics , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics , Shanghai , China","institution_ids":["https://openalex.org/I181679659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9872999787330627,"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":0.9872999787330627,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.007400000002235174,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0012000000569969416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.8870000243186951},{"id":"https://openalex.org/keywords/prior-data-fitted-networks","display_name":"prior-data fitted networks","score":0.8240000009536743},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7630000114440918},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.492000013589859},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063999772071838},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7053999900817871},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6144000291824341},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5582000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404999852180481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5306000113487244},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4666999876499176},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C186116695","wikidata":"https://www.wikidata.org/wiki/Q5249226","display_name":"Decision analysis","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.34035","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.34035","pdf_url":"https://arxiv.org/pdf/2610.34035","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.2610.34035","doi":"https://doi.org/10.48550/arxiv.2610.34035","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.34035","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:2610.34035","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.34035","pdf_url":"https://arxiv.org/pdf/2610.34035","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223845342.pdf","grobid_xml":"https://content.openalex.org/works/W7223845342.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7213412166"],"related_works":["https://openalex.org/W4389072753","https://openalex.org/W2810033056","https://openalex.org/W4415796044","https://openalex.org/W3133218073","https://openalex.org/W4397028408","https://openalex.org/W6889779352","https://openalex.org/W7113492690","https://openalex.org/W3094224826","https://openalex.org/W4400104495","https://openalex.org/W4382203490"],"abstract_inverted_index":{"Off-policy":[0],"evaluation":[1],"(OPE)":[2],"is":[3,14],"essential":[4],"for":[5,79,125],"assessing":[6],"decision":[7,66,85],"policies":[8],"before":[9],"deployment":[10],"when":[11,22],"online":[12],"experimentation":[13],"costly":[15],"or":[16],"unsafe.":[17],"Accurate":[18],"estimation":[19],"remains":[20],"difficult":[21],"behavior-policy":[23,73,92],"data":[24],"are":[25],"limited":[26],"and":[27,33,68,75,96],"the":[28,87,91,104],"target":[29,94],"policy":[30,70],"favors":[31],"states":[32],"actions":[34],"rarely":[35],"observed":[36],"in":[37],"those":[38],"data.":[39],"We":[40,58],"propose":[41],"InCOPE,":[42],"a":[43,49,82,118],"prior-data":[44],"fitted":[45],"network":[46,89],"that":[47],"learns":[48],"shared":[50],"policy-value":[51,126],"prediction":[52],"rule":[53],"across":[54,113],"synthetic":[55],"OPE":[56,61],"tasks.":[57],"construct":[59],"an":[60],"task":[62,98],"prior":[63],"over":[64],"Markov":[65],"processes":[67],"behavior-target":[69],"pairs,":[71],"generating":[72],"datasets":[74],"exact":[76],"target-policy":[77],"values":[78],"pretraining.":[80],"For":[81],"new":[83],"tabular":[84,115],"problem,":[86],"pretrained":[88],"uses":[90],"dataset,":[93],"policy,":[95],"known":[97],"settings":[99],"as":[100],"context":[101],"to":[102],"predict":[103],"policy's":[105],"expected":[106],"return":[107],"without":[108],"task-specific":[109],"parameter":[110],"updates.":[111],"Experiments":[112],"four":[114],"domains,":[116],"including":[117],"semi-synthetic":[119],"clinical":[120],"setting,":[121],"demonstrate":[122],"InCOPE's":[123],"effectiveness":[124],"estimation.":[127]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-28T00:00:00"}