{"id":"https://openalex.org/W2558801266","doi":"https://doi.org/10.24963/ijcai.2017/32","title":"The Off-Switch Game","display_name":"The Off-Switch Game","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2558801266","doi":"https://doi.org/10.24963/ijcai.2017/32","mag":"2558801266"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/32","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/32","pdf_url":"https://www.ijcai.org/proceedings/2017/0032.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0032.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076757561","display_name":"Dylan Hadfield-Menell","orcid":"https://orcid.org/0000-0002-6168-4763"},"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":"Dylan Hadfield-Menell","raw_affiliation_strings":["University of California, Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466"},"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":"Anca Dragan","raw_affiliation_strings":["University of California, Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]},{"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":"Pieter Abbeel","raw_affiliation_strings":["International Computer Science Institute (ICSI)","OpenAI","University of California, Berkeley","University of California, Berkeley and OpenAI and International Computer Science Institute#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute (ICSI)","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"OpenAI","institution_ids":["https://openalex.org/I4210161460"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley and OpenAI and International Computer Science Institute#TAB#","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I4210161460","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007305440","display_name":"Stuart Russell","orcid":"https://orcid.org/0000-0001-5252-4306"},"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":"Stuart Russell","raw_affiliation_strings":["University of California, Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3449,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8925884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9332000017166138,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9332000017166138,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11810","display_name":"Complex Systems and Decision Making","score":0.9319999814033508,"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/T11031","display_name":"Game Theory and Applications","score":0.9305999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/incentive","display_name":"Incentive","score":0.8676985502243042},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.6650023460388184},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6289782524108887},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.5801367163658142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5581592917442322},{"id":"https://openalex.org/keywords/rational-agent","display_name":"Rational agent","score":0.5536181926727295},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5115562081336975},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.4390369653701782},{"id":"https://openalex.org/keywords/instinct","display_name":"Instinct","score":0.42785072326660156},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.41768965125083923},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.34143325686454773},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.34089523553848267},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.25978952646255493},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.20725324749946594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1870359480381012}],"concepts":[{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.8676985502243042},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.6650023460388184},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6289782524108887},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.5801367163658142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5581592917442322},{"id":"https://openalex.org/C31772880","wikidata":"https://www.wikidata.org/wiki/Q2666479","display_name":"Rational agent","level":2,"score":0.5536181926727295},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5115562081336975},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.4390369653701782},{"id":"https://openalex.org/C3232509","wikidata":"https://www.wikidata.org/wiki/Q18237","display_name":"Instinct","level":2,"score":0.42785072326660156},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.41768965125083923},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.34143325686454773},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.34089523553848267},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25978952646255493},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.20725324749946594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1870359480381012},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2017/32","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/32","pdf_url":"https://www.ijcai.org/proceedings/2017/0032.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1611.08219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1611.08219","pdf_url":"https://arxiv.org/pdf/1611.08219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2558801266","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1611.08219.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1611.08219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1611.08219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"mag:2996337238","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/aaai/aaai2017w.html#Hadfield-Menell17","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/32","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/32","pdf_url":"https://www.ijcai.org/proceedings/2017/0032.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2465514544","display_name":"Graduate Research Fellowship Program","funder_award_id":"1106400","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4983093386","display_name":"CAREER:  Towards Autonomously Generating Robot Behavior for Coordination with Humans -- Accounting for Effects on Human Actions","funder_award_id":"1652083","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5883729437","display_name":null,"funder_award_id":"Grant No. DGE 1106400","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7972530987","display_name":null,"funder_award_id":"DGE 1106400","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320317463","display_name":"Future of Life Institute","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2558801266.pdf","grobid_xml":"https://content.openalex.org/works/W2558801266.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W145787216","https://openalex.org/W1534895963","https://openalex.org/W1581742186","https://openalex.org/W1838394841","https://openalex.org/W1983362322","https://openalex.org/W2025045042","https://openalex.org/W2163246690","https://openalex.org/W2174179791","https://openalex.org/W2399852338","https://openalex.org/W2410842990","https://openalex.org/W2574075983"],"related_works":["https://openalex.org/W2962937807","https://openalex.org/W2574075983","https://openalex.org/W2462906003","https://openalex.org/W1581742186","https://openalex.org/W2997799538","https://openalex.org/W3104717612","https://openalex.org/W16554708","https://openalex.org/W2914559550","https://openalex.org/W2071085248","https://openalex.org/W2795174724","https://openalex.org/W2269689645","https://openalex.org/W2268220849","https://openalex.org/W3104980690","https://openalex.org/W2132979545","https://openalex.org/W2399294555","https://openalex.org/W2070037214","https://openalex.org/W3169861345","https://openalex.org/W2951605358","https://openalex.org/W5206641","https://openalex.org/W2136246485"],"abstract_inverted_index":{"It":[0],"is":[1,22,38,59,74,101,105,176,182,251],"clear":[2],"that":[3,42,49,158,183,214,230,248],"one":[4],"of":[5,33,65,236,255,260],"the":[6,14,23,27,31,55,108,144,166,171,199,203,256],"primary":[7],"tools":[8],"we":[9,156,246],"can":[10,135,142],"use":[11],"to":[12,25,40,106,113,116,164,186,188,195,206,221,242],"mitigate":[13],"potential":[15],"risk":[16],"from":[17,53],"a":[18,51,60,78,83,122,126,130,252],"misbehaving":[19],"AI":[20,34,258],"system":[21,28,56],"ability":[24],"turn":[26],"off.":[29,57,119],"As":[30],"capabilities":[32],"systems":[35,44],"improve,":[36],"it":[37,95,100,193],"important":[39,211],"ensure":[41],"such":[43,159],"do":[45],"not":[46,75],"adopt":[47],"subgoals":[48],"prevent":[50],"human":[52,127],"switching":[54],"This":[58,73],"challenge":[61],"because":[62,82],"many":[63],"formulations":[64],"rational":[66,84,261],"agents":[67,160],"create":[68],"strong":[69],"incentives":[70,109],"for":[71,154,184],"self-preservation.":[72],"caused":[76],"by":[77],"built-in":[79],"instinct,":[80],"but":[81,140],"agent":[85,111,149],"will":[86],"maximize":[87],"expected":[88],"utility":[89,200],"and":[90,129,205,245],"cannot":[91],"achieve":[92],"whatever":[93],"objective":[94],"has":[96,112,218],"been":[97],"given":[98],"if":[99],"dead.":[102],"Our":[103,179],"goal":[104],"study":[107],"an":[110,162,233],"allow":[114],"itself":[115,223],"be":[117,196],"switched":[118],"We":[120,228],"analyze":[121],"simple":[123],"game":[124],"between":[125],"H":[128,134,175],"robot":[131],"R,":[132],"where":[133,174],"press":[136],"R\u2019s":[137],"off":[138,145,167,191,224],"switch":[139,222],"R":[141,185],"disable":[143,165],"switch.":[146],"A":[147],"traditional":[148],"takes":[150],"its":[151,190],"reward":[152],"function":[153],"granted:":[155],"show":[157],"have":[161],"incentive":[163,220],"switch,":[168,192],"except":[169],"in":[170,225],"special":[172],"case":[173],"perfectly":[177],"rational.":[178],"key":[180],"insight":[181],"want":[187],"preserve":[189],"needs":[194],"uncertain":[197],"about":[198,213,238],"associated":[201],"with":[202],"outcome,":[204],"treat":[207],"H\u2019s":[208],"actions":[209],"as":[210],"observations":[212],"utility.":[215],"(R":[216],"also":[217],"no":[219],"this":[226,249],"setting.)":[227],"conclude":[229],"giving":[231],"machines":[232],"appropriate":[234],"level":[235],"uncertainty":[237],"their":[239],"objectives":[240],"leads":[241],"safer":[243],"designs,":[244],"argue":[247],"setting":[250],"useful":[253],"generalization":[254],"classical":[257],"paradigm":[259],"agents.":[262]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}
