{"id":"https://openalex.org/W2916350282","doi":"https://doi.org/10.1145/3375627.3375851","title":"Conservative Agency via Attainable Utility Preservation","display_name":"Conservative Agency via Attainable Utility Preservation","publication_year":2020,"publication_date":"2020-02-05","ids":{"openalex":"https://openalex.org/W2916350282","doi":"https://doi.org/10.1145/3375627.3375851","mag":"2916350282"},"language":"en","primary_location":{"id":"doi:10.1145/3375627.3375851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3375627.3375851","pdf_url":null,"source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.09725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alexander Matt Turner","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander Matt Turner","raw_affiliation_strings":["Oregon State University, Corvallis, OR, USA"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dylan Hadfield-Menell","orcid":null},"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, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Prasad Tadepalli","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasad Tadepalli","raw_affiliation_strings":["Oregon State University, Corvallis, OR, USA"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":0.8663,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7834346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.2337000072002411,"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/T10142","display_name":"Formal Methods in Verification","score":0.2337000072002411,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20080000162124634,"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":0.08699999749660492,"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/function","display_name":"Function (biology)","score":0.6743000149726868},{"id":"https://openalex.org/keywords/agency","display_name":"Agency (philosophy)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.3310999870300293},{"id":"https://openalex.org/keywords/factory","display_name":"Factory (object-oriented programming)","score":0.2989000082015991}],"concepts":[{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.521399974822998},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.33000001311302185},{"id":"https://openalex.org/C40149104","wikidata":"https://www.wikidata.org/wiki/Q5620977","display_name":"Factory (object-oriented programming)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2728999853134155}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3375627.3375851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3375627.3375851","pdf_url":null,"source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.09725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.09725","pdf_url":"https://arxiv.org/pdf/1902.09725","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.09725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.09725","pdf_url":"https://arxiv.org/pdf/1902.09725","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1541317966","https://openalex.org/W2151237105","https://openalex.org/W2181068523","https://openalex.org/W2257979135","https://openalex.org/W2288565641","https://openalex.org/W2410842990","https://openalex.org/W2618318883","https://openalex.org/W2626804490","https://openalex.org/W2736629007","https://openalex.org/W2769541360","https://openalex.org/W2803543472","https://openalex.org/W2808155616","https://openalex.org/W2962937807","https://openalex.org/W2963943581","https://openalex.org/W3003931103","https://openalex.org/W6743368274"],"related_works":[],"abstract_inverted_index":{"Reward":[0],"functions":[1,104],"are":[2,105],"easy":[3],"to":[4,55,93],"misspecify;":[5],"although":[6],"designers":[7,62],"can":[8,21],"make":[9],"corrections":[10],"after":[11],"observing":[12],"mistakes,":[13],"an":[14,78],"agent":[15],"pursuing":[16],"a":[17,46,56],"misspecified":[18],"reward":[19,38,57,66,86,96,103,115],"function":[20,87],"irreversibly":[22],"change":[23,31],"the":[24,35,61,65,68,84,91,101,112],"state":[25],"of":[26,34,83,90],"its":[27],"environment.":[28],"If":[29],"that":[30,80],"precludes":[32],"optimization":[33,82],"correctly":[36,113],"specified":[37,114],"function,":[39,67,116],"then":[40],"correction":[41],"is":[42,70],"futile.":[43],"For":[44],"example,":[45],"robotic":[47],"factory":[48],"assistant":[49],"could":[50],"break":[51],"expensive":[52],"equipment":[53],"due":[54],"misspecification;":[58],"even":[59,99],"if":[60],"immediately":[63],"correct":[64],"damage":[69],"done.":[71],"To":[72],"mitigate":[73],"this":[74,117],"risk,":[75],"we":[76],"introduce":[77],"approach":[79,118],"balances":[81],"primary":[85],"with":[88],"preservation":[89],"ability":[92],"optimize":[94],"auxiliary":[95,102],"functions.":[97],"Surprisingly,":[98],"when":[100],"randomly":[106],"generated":[107],"and":[108],"therefore":[109],"uninformative":[110],"about":[111],"induces":[119],"conservative,":[120],"effective":[121],"behavior.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-03-02T00:00:00"}