{"id":"https://openalex.org/W2187230862","doi":null,"title":"Self-Modeling Agents and Reward Generator Corruption","display_name":"Self-Modeling Agents and Reward Generator Corruption","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2187230862","mag":"2187230862"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.694.521","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.694.521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ssec.wisc.edu/%7Ebillh/g/hibbard_aaai_2015.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109350921","display_name":"Bill Hibbard","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bill Hibbard","raw_affiliation_strings":["University of Wisconsin-Madison, #TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, #TAB#","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109350921"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.8848,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77933262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5332000255584717,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5332000255584717,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.13660000264644623,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09229999780654907,"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/universal-artificial-intelligence","display_name":"universal artificial intelligence","score":0.8009999990463257},{"id":"https://openalex.org/keywords/solomonoff-induction","display_name":"Solomonoff induction","score":0.7519999742507935},{"id":"https://openalex.org/keywords/sequence-prediction","display_name":"sequence prediction","score":0.7670000195503235},{"id":"https://openalex.org/keywords/agent-environment-interaction","display_name":"agent-environment interaction","score":0.7480000257492065},{"id":"https://openalex.org/keywords/reward-maximization","display_name":"reward maximization","score":0.5199999809265137},{"id":"https://openalex.org/keywords/ethical-artificial-intelligence","display_name":"ethical artificial intelligence","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.744513213634491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6395182013511658},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.632638156414032},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6119915246963501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5535929799079895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06586763262748718},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.694.521","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.694.521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ssec.wisc.edu/%7Ebillh/g/hibbard_aaai_2015.pdf","raw_type":"text"},{"id":"mag:2187230862","doi":null,"is_oa":false,"landing_page_url":"https://www.ssec.wisc.edu/~billh/g/hibbard_aaai_2015.pdf","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,"listed_in":[],"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":false,"raw_source_name":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W181665514","https://openalex.org/W355895575","https://openalex.org/W1581742186","https://openalex.org/W1624823515","https://openalex.org/W1757796397","https://openalex.org/W1772262888","https://openalex.org/W1899824525","https://openalex.org/W1993466133","https://openalex.org/W2010936689","https://openalex.org/W2013391942","https://openalex.org/W2025440394","https://openalex.org/W2095935193","https://openalex.org/W2122410182","https://openalex.org/W2344349788"],"related_works":["https://openalex.org/W1772262888","https://openalex.org/W7167788849","https://openalex.org/W355895575","https://openalex.org/W7112373900","https://openalex.org/W4391710028","https://openalex.org/W7115172585","https://openalex.org/W2010936689","https://openalex.org/W7165658118","https://openalex.org/W7202250479","https://openalex.org/W145282967"],"abstract_inverted_index":{"Hutter's":[0],"universal":[1],"artificial":[2],"intelligence":[3],"(AI)":[4],"showed":[5],"how":[6],"to":[7,20,61,116,119,162,190,203],"define":[8,21,124,227],"future":[9,35,127],"AI":[10,26,42,99,128],"systems":[11,27,129],"by":[12,47],"mathematical":[13,121],"equations.":[14],"Here":[15,56],"we":[16,57],"adapt":[17],"those":[18],"equations":[19,122],"a":[22,59,96,141,256],"self-modeling":[23,67],"framework,":[24],"where":[25,175,195],"learn":[28],"models":[29],"of":[30,34,51,75,83,113,126,145,217,235,242,255],"their":[31],"own":[32],"calculations":[33],"values.":[36],"Hutter":[37,109],"discussed":[38],"the":[39,49,54,66,73,84,163,173,196,215,233,236,248,253],"possibility":[40],"that":[41,123,133,222],"agents":[43,100],"may":[44],"maximize":[45],"rewards":[46,52],"corrupting":[48],"source":[50],"in":[53,65,72,140,201],"environment.":[55],"propose":[58],"way":[60],"avoid":[62],"such":[63],"corruption":[64],"framework.":[68],"This":[69],"paper":[70],"fits":[71],"context":[74],"my":[76],"book":[77,85],"Ethical":[78],"Artificial":[79],"Intelligence.":[80],"A":[81,161,176],"draft":[82],"is":[86],"available":[87],"at:":[88],"arxiv.org/abs/1411.1373.":[89],"Self-Modeling":[90],"Agents":[91],"Russell":[92],"and":[93,106,165,177,226],"Norvig":[94,107],"defined":[95],"framework":[97,118],"for":[98,206],"interacting":[101],"with":[102,137],"an":[103,134,157,167,192],"environment":[104,139,164,197,250],"(Russell":[105],"2010).":[108],"adapted":[110],"Solomonoff's":[111],"theory":[112],"sequence":[114],"prediction":[115],"this":[117],"produce":[120],"behaviors":[125],"(Hutter":[130],"2005).":[131],"Assume":[132],"agent":[135,155],"interacts":[136],"its":[138,243],"discrete,":[142],"finite":[143,180,219],"series":[144],"time":[146],"steps":[147],"t":[148,231],"\u2208":[149,160,170,224],"{0,":[150],"1,":[151],"2,...,":[152],"T}.":[153],"The":[154],"sends":[156],"action":[158,204],"at":[159],"receives":[166],"observation":[168,199],"ot":[169],"O":[171,178],"from":[172],"environment,":[174],"are":[179,245],"sets.":[181],"We":[182],"use":[183],"h":[184,223],"=":[185,230],"(a1,":[186],"o1,...,":[187],"at,":[188],"ot)":[189],"denote":[191],"interaction":[193,260],"history":[194,237],"produces":[198],"oi":[200],"response":[202],"ai":[205],"1":[207],"\u2264":[208,210],"i":[209],"t.":[211],"Let":[212],"H":[213,264],"be":[214],"set":[216],"all":[218],"histories":[220],"so":[221,247],"H,":[225],"|h":[228],"|":[229],"as":[232],"length":[234],"h.":[238],"An":[239],"agent's":[240,249],"predictions":[241],"observations":[244],"uncertain":[246],"model":[251],"takes":[252],"form":[254],"probability":[257],"distribution":[258],"over":[259],"histories:":[261],"(1)":[262],"\u03c1:":[263],"\u2192":[265],"[0,":[266],"1].":[267]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}