{"id":"https://openalex.org/W3162665177","doi":"https://doi.org/10.1109/jsait.2021.3079722","title":"Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent","display_name":"Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent","publication_year":2021,"publication_date":"2021-05-14","ids":{"openalex":"https://openalex.org/W3162665177","doi":"https://doi.org/10.1109/jsait.2021.3079722","mag":"3162665177"},"language":"en","primary_location":{"id":"doi:10.1109/jsait.2021.3079722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsait.2021.3079722","pdf_url":null,"source":{"id":"https://openalex.org/S4210211895","display_name":"IEEE Journal on Selected Areas in Information Theory","issn_l":"2641-8770","issn":["2641-8770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5027690597","display_name":"Michael K. Cohen","orcid":"https://orcid.org/0000-0003-1749-875X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Michael K. Cohen","raw_affiliation_strings":["Oxford University, Oxford, U.K"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020795308","display_name":"Elliot Catt","orcid":"https://orcid.org/0000-0001-9411-927X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Elliot Catt","raw_affiliation_strings":["Research School of Computer Science, Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073944062","display_name":"Marcus H\u00fctter","orcid":"https://orcid.org/0000-0002-3263-4097"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Marcus Hutter","raw_affiliation_strings":["Australian National University, Canberra, ACT, Australia","Google DeepMind, London, U.K"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Google DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027690597"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06147682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"2","first_page":"665","last_page":"677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9908999800682068,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9882000088691711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7888938188552856},{"id":"https://openalex.org/keywords/ergodicity","display_name":"Ergodicity","score":0.7798233032226562},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.7269641160964966},{"id":"https://openalex.org/keywords/asymptotically-optimal-algorithm","display_name":"Asymptotically optimal algorithm","score":0.6304923295974731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614395797252655},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5465975403785706},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5169607996940613},{"id":"https://openalex.org/keywords/ergodic-theory","display_name":"Ergodic theory","score":0.5136165022850037},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3626253008842468},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3248705565929413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2969610095024109},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2388361692428589},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15250149369239807},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10421004891395569},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09681877493858337}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7888938188552856},{"id":"https://openalex.org/C201779956","wikidata":"https://www.wikidata.org/wiki/Q5426803","display_name":"Ergodicity","level":2,"score":0.7798233032226562},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.7269641160964966},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.6304923295974731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614395797252655},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5465975403785706},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5169607996940613},{"id":"https://openalex.org/C122044880","wikidata":"https://www.wikidata.org/wiki/Q5498822","display_name":"Ergodic theory","level":2,"score":0.5136165022850037},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3626253008842468},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3248705565929413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2969610095024109},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2388361692428589},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15250149369239807},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10421004891395569},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09681877493858337},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jsait.2021.3079722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsait.2021.3079722","pdf_url":null,"source":{"id":"https://openalex.org/S4210211895","display_name":"IEEE Journal on Selected Areas in Information Theory","issn_l":"2641-8770","issn":["2641-8770"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Information Theory","raw_type":"journal-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/316646","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/316646","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal on Selected Areas in Information Theory","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G144560564","display_name":null,"funder_award_id":"DP150104590","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W121023703","https://openalex.org/W134786152","https://openalex.org/W1497976081","https://openalex.org/W1539975474","https://openalex.org/W1540685400","https://openalex.org/W1585575029","https://openalex.org/W1589064538","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W1876044947","https://openalex.org/W1915057100","https://openalex.org/W1917036087","https://openalex.org/W1919575688","https://openalex.org/W1931877416","https://openalex.org/W1965878388","https://openalex.org/W1999874108","https://openalex.org/W2013391942","https://openalex.org/W2013953457","https://openalex.org/W2039522160","https://openalex.org/W2070301851","https://openalex.org/W2113023245","https://openalex.org/W2132322771","https://openalex.org/W2136661843","https://openalex.org/W2137509429","https://openalex.org/W2144863733","https://openalex.org/W2162849300","https://openalex.org/W2281341692","https://openalex.org/W2427917354","https://openalex.org/W2462906003","https://openalex.org/W2558819991","https://openalex.org/W2575120333","https://openalex.org/W2606508169","https://openalex.org/W2617291496","https://openalex.org/W2736629007","https://openalex.org/W2772878991","https://openalex.org/W2952720101","https://openalex.org/W2962957031","https://openalex.org/W2962973228","https://openalex.org/W2962977206","https://openalex.org/W2963277051","https://openalex.org/W2963505878","https://openalex.org/W2963958573","https://openalex.org/W2964108562","https://openalex.org/W2964273112","https://openalex.org/W2964325826","https://openalex.org/W2966368748","https://openalex.org/W2997702520","https://openalex.org/W3104013016","https://openalex.org/W4237705481","https://openalex.org/W4293775587","https://openalex.org/W4297748582","https://openalex.org/W4297780563","https://openalex.org/W4299502902","https://openalex.org/W4394644466","https://openalex.org/W6600644339","https://openalex.org/W6604963999","https://openalex.org/W6632235069","https://openalex.org/W6632444001","https://openalex.org/W6635457194","https://openalex.org/W6639145154","https://openalex.org/W6640174482","https://openalex.org/W6640399833","https://openalex.org/W6676728370","https://openalex.org/W6683397050","https://openalex.org/W6695243658","https://openalex.org/W6717915398","https://openalex.org/W6718092244"],"related_works":["https://openalex.org/W1972942382","https://openalex.org/W2009962825","https://openalex.org/W124275629","https://openalex.org/W2136727990","https://openalex.org/W1722744795","https://openalex.org/W2950014027","https://openalex.org/W2952991236","https://openalex.org/W964575223","https://openalex.org/W4296948412","https://openalex.org/W2358718285"],"abstract_inverted_index":{"Reinforcement":[0],"learners":[1],"are":[2],"agents":[3,126,187],"that":[4,9,37],"learn":[5],"to":[6,11,43,54,81,94],"pick":[7],"actions":[8],"lead":[10],"high":[12],"reward.":[13,33],"Ideally,":[14],"the":[15,24,29,58,100,106,134,142,147,165],"value":[16],"of":[17,102,145,149,156],"a":[18,150,172,177],"reinforcement":[19,75,110],"learner's":[20],"policy":[21,27],"approaches":[22],"optimality-where":[23],"optimal":[25,186],"informed":[26],"is":[28,41],"one":[30],"which":[31],"maximizes":[32],"Unfortunately,":[34],"we":[35,136,180],"show":[36],"if":[38],"an":[39,55,78,138],"agent":[40,62],"guaranteed":[42],"be":[44,64],"\u201casymptotically":[45],"optimal\u201d":[46],"in":[47,74,99,109,118,127],"any":[48],"(stochastically":[49],"computable)":[50],"environment,":[51,60],"then":[52],"subject":[53],"assumption":[56,80,108],"about":[57],"true":[59],"this":[61,83],"will":[63],"either":[65],"\u201cdestroyed\u201d":[66],"or":[67],"\u201cincapacitated\u201d":[68],"with":[69,141,176],"probability":[70,162],"1.":[71],"Much":[72],"work":[73],"learning":[76,111],"uses":[77],"ergodicity":[79,107],"avoid":[82],"problem.":[84],"Often,":[85],"doing":[86,152],"theoretical":[87],"research":[88],"under":[89],"simplifying":[90],"assumptions":[91],"prepares":[92],"us":[93,115],"provide":[95],"practical":[96],"solutions":[97],"even":[98],"absence":[101],"those":[103],"assumptions,":[104],"but":[105],"may":[112],"have":[113],"led":[114],"entirely":[116],"astray":[117],"preparing":[119],"safe":[120,153],"and":[121,188],"effective":[122],"exploration":[123,154,161],"strategies":[124],"for":[125],"dangerous":[128],"environments.":[129],"Rather":[130],"than":[131],"assuming":[132],"away":[133],"problem,":[135],"present":[137],"agent,":[139],"Mentee,":[140],"modest":[143],"guarantee":[144],"approaching":[146],"performance":[148],"mentor,":[151,179],"instead":[155],"reckless":[157],"exploration.":[158],"Critically,":[159],"Mentee's":[160],"depends":[163],"on":[164],"expected":[166],"information":[167],"gain":[168],"from":[169],"exploring.":[170],"In":[171],"simple":[173],"non-ergodic":[174],"environment":[175],"weak":[178],"find":[181],"Mentee":[182],"outperforms":[183],"existing":[184],"asymptotically":[185],"its":[189],"mentor.":[190]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}