{"id":"https://openalex.org/W4307323396","doi":"https://doi.org/10.48550/arxiv.2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","display_name":"Dichotomy of Control: Separating What You Can Control from What You Cannot","publication_year":2022,"publication_date":"2022-10-24","ids":{"openalex":"https://openalex.org/W4307323396","doi":"https://doi.org/10.48550/arxiv.2210.13435"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.13435","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.13435","pdf_url":"https://arxiv.org/pdf/2210.13435","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/2210.13435","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100546518","display_name":"Mengjiao Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Mengjiao","raw_affiliation_strings":["University of California , Berkeley Google Research , Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley Google Research , Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010575626","display_name":"Dale Schuurmans","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Schuurmans, Dale","raw_affiliation_strings":["University of Alberta Google Research , Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta Google Research , Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":"https://orcid.org/0009-0007-0628-9932","observed_orcids":["https://orcid.org/0009-0007-0628-9932"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abbeel, Pieter","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057773393","display_name":"Ofir Nachum","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nachum, Ofir","raw_affiliation_strings":["Google Research , Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Brain Team","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":32,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.7680000066757202},{"id":"https://openalex.org/keywords/decision-transformer","display_name":"decision transformer","score":0.7770000100135803},{"id":"https://openalex.org/keywords/mutual-information-constraint","display_name":"mutual information constraint","score":0.9829999804496765},{"id":"https://openalex.org/keywords/policy-coherence","display_name":"policy coherence","score":0.5490000247955322},{"id":"https://openalex.org/keywords/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.7631064057350159},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7013260722160339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5983337163925171},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5750895738601685},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.5478342771530151},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.5444612503051758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46601584553718567},{"id":"https://openalex.org/C154611145","wikidata":"https://www.wikidata.org/wiki/Q4331879","display_name":"Expected return","level":3,"score":0.45151758193969727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4455483853816986},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4356954097747803},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.41227802634239197},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4104500114917755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39050671458244324},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.19947683811187744},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.18132108449935913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17568901181221008},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1569163203239441},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.14892536401748657},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1261301040649414},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.11873689293861389},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11391344666481018},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.09600073099136353},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.09216657280921936},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.13435","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.13435","pdf_url":"https://arxiv.org/pdf/2210.13435","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.2210.13435","doi":"https://doi.org/10.48550/arxiv.2210.13435","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.13435","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":"pmh:oai:arXiv.org:2210.13435","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.13435","pdf_url":"https://arxiv.org/pdf/2210.13435","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":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307323396.pdf","grobid_xml":"https://content.openalex.org/works/W4307323396.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1959608418","https://openalex.org/W2605016475","https://openalex.org/W2976023236","https://openalex.org/W2991355586","https://openalex.org/W2992155277","https://openalex.org/W2993446282","https://openalex.org/W2997876358","https://openalex.org/W3016525976","https://openalex.org/W3034767611","https://openalex.org/W3037207827","https://openalex.org/W3094484961","https://openalex.org/W3096964654","https://openalex.org/W3101483449","https://openalex.org/W3113014242","https://openalex.org/W3122543654","https://openalex.org/W3183876471","https://openalex.org/W3188460932","https://openalex.org/W3192145739","https://openalex.org/W3216752036","https://openalex.org/W4221142845","https://openalex.org/W4226395791","https://openalex.org/W4307868887","https://openalex.org/W4320351063","https://openalex.org/W7103485097","https://openalex.org/W7133190548","https://openalex.org/W7133196022","https://openalex.org/W7133197435","https://openalex.org/W7133238060","https://openalex.org/W7133261304"],"related_works":["https://openalex.org/W7133196022","https://openalex.org/W4417137002","https://openalex.org/W4378715832","https://openalex.org/W4416235028","https://openalex.org/W4417266226","https://openalex.org/W2945703303","https://openalex.org/W4388093345","https://openalex.org/W7167807321","https://openalex.org/W3188460932","https://openalex.org/W4387635276"],"abstract_inverted_index":{"Future-":[0],"or":[1],"return-conditioned":[2],"supervised":[3,136],"learning":[4,12,137],"is":[5,26,41,89,119,227],"an":[6,22,64],"emerging":[7],"paradigm":[8],"for":[9],"offline":[10],"reinforcement":[11],"(RL),":[13],"where":[14,63],"the":[15,43,73,77,97,102,129,161,169,182,189],"future":[16,215],"outcome":[17,216],"(i.e.,":[18],"return)":[19],"associated":[20,185],"with":[21,91,186,201],"observed":[23],"action":[24],"sequence":[25],"used":[27],"as":[28,49],"input":[29],"to":[30,34,56,84,99,112,229],"a":[31,85,107,113,134,143,150,164,173,208,212],"policy":[32,87,98,162,210],"trained":[33],"imitate":[35],"those":[36,148],"same":[37],"actions.":[38],"While":[39],"return-conditioning":[40],"at":[42],"heart":[44],"of":[45,115,131,168],"popular":[46],"algorithms":[47],"such":[48],"decision":[50],"transformer":[51],"(DT),":[52],"these":[53],"methods":[54],"tend":[55],"perform":[57],"poorly":[58],"in":[59,72,101,188],"highly":[60,240],"stochastic":[61,241],"environments,":[62],"occasional":[65],"high":[66],"return":[67],"can":[68,82],"arise":[69],"from":[70,147,181],"randomness":[71,187],"environment":[74],"rather":[75],"than":[76,122,234],"actions":[78],"themselves.":[79],"Such":[80],"situations":[81],"lead":[83],"learned":[86,209],"that":[88,118,139,177,194,198,206,225,238],"inconsistent":[90],"its":[92],"conditioning":[93,105,160,203,207],"inputs;":[94],"i.e.,":[95],"using":[96],"act":[100],"environment,":[103],"when":[104],"on":[106,163,211,236],"specific":[108],"desired":[109,213],"return,":[110],"leads":[111],"distribution":[114],"real":[116],"returns":[117],"wildly":[120],"different":[121],"desired.":[123],"In":[124],"this":[125,157],"work,":[126],"we":[127,192,223],"propose":[128],"dichotomy":[130],"control":[132,145,152],"(DoC),":[133],"future-conditioned":[135],"framework":[138],"separates":[140],"mechanisms":[141],"within":[142],"policy's":[144,151],"(actions)":[146],"beyond":[149],"(environment":[153],"stochasticity).":[154],"We":[155],"achieve":[156,230],"separation":[158],"by":[159],"latent":[165,183],"variable":[166,184],"representation":[167],"future,":[170],"and":[171,243],"designing":[172],"mutual":[174],"information":[175,180],"constraint":[176],"removes":[178],"any":[179],"environment.":[190],"Theoretically,":[191],"show":[193,224],"DoC":[195,226],"yields":[196],"policies":[197],"are":[199],"consistent":[200],"their":[202],"inputs,":[204],"ensuring":[205],"high-return":[214,220],"will":[217],"correctly":[218],"induce":[219],"behavior.":[221],"Empirically,":[222],"able":[228],"significantly":[231],"better":[232],"performance":[233],"DT":[235],"environments":[237],"have":[239],"rewards":[242],"transition":[244]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-10-31T00:00:00"}