{"id":"https://openalex.org/W7204190380","doi":"https://doi.org/10.48550/arxiv.2608.22092","title":"Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does","display_name":"Counterfactual Quotient Models: Learning What Actions Change, Not What the World Does","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204190380","doi":"https://doi.org/10.48550/arxiv.2608.22092"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22092","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22092","pdf_url":"https://arxiv.org/pdf/2608.22092","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148104178","display_name":"Junlin Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Junlin","raw_affiliation_strings":["School of Computer Science and Engineering , Beihang University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Beihang University Beijing , China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128432124","display_name":"Ruijie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Ruijie","raw_affiliation_strings":["School of Computer Science and Engineering , Beihang University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Beihang University Beijing , China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148149811","display_name":"Jianxin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Jianxin","raw_affiliation_strings":["School of Computer Science and Engineering , Beihang University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Beihang University Beijing , China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","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/identifiability","display_name":"identifiability","score":0.6520000100135803},{"id":"https://openalex.org/keywords/regret-analysis","display_name":"regret analysis","score":0.5899999737739563},{"id":"https://openalex.org/keywords/reinforcement-learning-models","display_name":"reinforcement learning models","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8615000247955322},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49300000071525574},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4862000048160553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3723999857902527},{"id":"https://openalex.org/C199422724","wikidata":"https://www.wikidata.org/wiki/Q41118","display_name":"Quotient","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C58315980","wikidata":"https://www.wikidata.org/wiki/Q179436","display_name":"Asymptote","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25839999318122864},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22092","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22092","pdf_url":"https://arxiv.org/pdf/2608.22092","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.2608.22092","doi":"https://doi.org/10.48550/arxiv.2608.22092","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22092","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:2608.22092","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22092","pdf_url":"https://arxiv.org/pdf/2608.22092","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/W7204190380.pdf","grobid_xml":"https://content.openalex.org/works/W7204190380.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3099551617","https://openalex.org/W7133206212","https://openalex.org/W7097785347","https://openalex.org/W2594533284","https://openalex.org/W7222924149","https://openalex.org/W3114476669","https://openalex.org/W7204202063","https://openalex.org/W7203679656","https://openalex.org/W7204891475","https://openalex.org/W2781942582"],"abstract_inverted_index":{"Reinforcement-learning":[0],"models":[1,29,163],"commonly":[2],"predict":[3,166],"complete":[4,113],"future":[5],"states,":[6],"observations,":[7],"or":[8],"feature":[9],"occupancies,":[10],"even":[11],"though":[12],"action":[13,82,159],"selection":[14],"depends":[15],"only":[16,63],"on":[17],"differences":[18],"between":[19],"the":[20,44,50,86,120,132],"consequences":[21],"of":[22,43,131],"candidate":[23],"actions.":[24,69],"As":[25],"a":[26,65],"result,":[27],"these":[28,94,144],"may":[30],"devote":[31],"substantial":[32],"statistical":[33],"and":[34,128,157],"representational":[35],"capacity":[36],"to":[37,162,165],"high-dimensional":[38],"phenomena":[39],"that":[40],"evolve":[41],"independently":[42],"agent's":[45],"current":[46],"choice.":[47],"We":[48,118],"introduce":[49],"Counterfactual":[51],"Quotient":[52],"Model,":[53],"which":[54],"treats":[55],"action-conditioned":[56],"futures":[57,114],"as":[58],"equivalent":[59],"when":[60],"they":[61],"differ":[62],"by":[64,85],"component":[66,77],"shared":[67,103],"across":[68],"Its":[70],"canonical":[71],"centered":[72],"representation":[73],"removes":[74],"this":[75],"common":[76],"while":[78],"preserving":[79],"every":[80],"pairwise":[81],"comparison":[83],"expressible":[84],"modeled":[87],"reward":[88,155],"family.":[89],"The":[90],"implemented":[91],"model":[92],"learns":[93],"action-dependent":[95],"effects":[96],"directly":[97],"from":[98],"synchronized":[99],"counterfactual":[100],"rollouts,":[101],"so":[102],"stochastic":[104],"dynamics":[105],"cancel":[106],"before":[107],"function":[108],"approximation":[109,126],"rather":[110],"than":[111],"after":[112],"have":[115],"been":[116],"predicted.":[117],"establish":[119],"decision":[121],"sufficiency,":[122],"identifiability,":[123],"common-mode":[124],"invariance,":[125],"behavior,":[127],"regret":[129],"properties":[130],"resulting":[133],"representation.":[134],"Controlled":[135],"experiments":[136],"in":[137],"physics-based":[138],"environments":[139],"provide":[140],"initial":[141],"evidence":[142],"for":[143],"properties:":[145],"direct":[146],"effect":[147],"learning":[148],"suppresses":[149],"action-independent":[150],"variation,":[151],"supports":[152],"previously":[153],"unseen":[154],"queries,":[156],"improves":[158],"ranking":[160],"relative":[161],"trained":[164],"absolute":[167],"futures.":[168]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}