{"id":"https://openalex.org/W4401354605","doi":"https://doi.org/10.1162/neco_a_01690","title":"Intrinsic Rewards for Exploration Without Harm From Observational Noise: A Simulation Study Based on the Free Energy Principle","display_name":"Intrinsic Rewards for Exploration Without Harm From Observational Noise: A Simulation Study Based on the Free Energy Principle","publication_year":2024,"publication_date":"2024-08-06","ids":{"openalex":"https://openalex.org/W4401354605","doi":"https://doi.org/10.1162/neco_a_01690","pmid":"https://pubmed.ncbi.nlm.nih.gov/39106455"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01690","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/neco_a_01690","pdf_url":"https://direct.mit.edu/neco/article-pdf/36/9/1854/2477511/neco_a_01690.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://direct.mit.edu/neco/article-pdf/36/9/1854/2477511/neco_a_01690.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098446449","display_name":"Theodore Jerome Tinker","orcid":null},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Theodore Jerome Tinker","raw_affiliation_strings":["Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University, Onna-san 904-0495, Okinawa, Japan theodore.tinker@oist.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University, Onna-san 904-0495, Okinawa, Japan theodore.tinker@oist.jp","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Onna-san 904-0495, Okinawa, Japan doya@oist.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Onna-san 904-0495, Okinawa, Japan doya@oist.jp","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000727773","display_name":"Jun Tani","orcid":"https://orcid.org/0000-0002-9131-9206"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Tani","raw_affiliation_strings":["Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University, Onna-san 904-0495, Okinawa, Japan jun.tani@oist.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University, Onna-san 904-0495, Okinawa, Japan jun.tani@oist.jp","institution_ids":["https://openalex.org/I142637625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5098446449"],"corresponding_institution_ids":["https://openalex.org/I142637625"],"apc_list":null,"apc_paid":null,"fwci":0.312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56671544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"9","first_page":"1854","last_page":"1885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.992900013923645,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.9832853674888611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6052390933036804},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5967099666595459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5518720746040344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5381051301956177},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4979069232940674},{"id":"https://openalex.org/keywords/observational-study","display_name":"Observational study","score":0.47791677713394165},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3173463046550751},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.19239109754562378},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14129599928855896},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0910668671131134}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9832853674888611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6052390933036804},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5967099666595459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5518720746040344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5381051301956177},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4979069232940674},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.47791677713394165},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3173463046550751},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.19239109754562378},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14129599928855896},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0910668671131134},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005106","descriptor_name":"Exploratory Behavior","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D005106","descriptor_name":"Exploratory Behavior","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D005106","descriptor_name":"Exploratory Behavior","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D005106","descriptor_name":"Exploratory Behavior","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01690","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/neco_a_01690","pdf_url":"https://direct.mit.edu/neco/article-pdf/36/9/1854/2477511/neco_a_01690.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:39106455","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39106455","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":{"id":"doi:10.1162/neco_a_01690","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/neco_a_01690","pdf_url":"https://direct.mit.edu/neco/article-pdf/36/9/1854/2477511/neco_a_01690.pdf","source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G7677580464","display_name":null,"funder_award_id":"JP23H04975","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401354605.pdf","grobid_xml":"https://content.openalex.org/works/W4401354605.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2000514530","https://openalex.org/W2005581799","https://openalex.org/W2028418738","https://openalex.org/W2034806191","https://openalex.org/W2039546655","https://openalex.org/W2076580309","https://openalex.org/W2091565802","https://openalex.org/W2111051539","https://openalex.org/W2145339207","https://openalex.org/W2316132413","https://openalex.org/W2463330366","https://openalex.org/W2559655401","https://openalex.org/W2781668895","https://openalex.org/W2892266804","https://openalex.org/W2963523627","https://openalex.org/W2974745023","https://openalex.org/W2976973594","https://openalex.org/W3001808890","https://openalex.org/W3090104579","https://openalex.org/W3095485376","https://openalex.org/W3210787633","https://openalex.org/W4220826180","https://openalex.org/W4362737158","https://openalex.org/W4385338481","https://openalex.org/W6638836233","https://openalex.org/W6650587873","https://openalex.org/W6684488266","https://openalex.org/W6770853193","https://openalex.org/W6803119889","https://openalex.org/W6851506684"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4401386752"],"abstract_inverted_index":{"In":[0],"reinforcement":[1],"learning":[2,210],"(RL),":[3],"artificial":[4,213],"agents":[5,21,77,87,114,134,139,147,175,187],"are":[6,33],"trained":[7,130],"to":[8,135],"maximize":[9],"numerical":[10],"rewards":[11,29,76,113,141],"by":[12,91,115],"performing":[13],"tasks.":[14],"Exploration":[15],"is":[16,45,56],"essential":[17],"in":[18,48,58,64,167],"RL":[19,205],"because":[20],"must":[22],"discover":[23],"information":[24,42],"before":[25],"exploiting":[26],"it.":[27],"Two":[28],"encouraging":[30],"efficient":[31,168],"exploration":[32],"the":[34,49,101,116,120,195,200,209],"entropy":[35,143,150,163],"of":[36,62,68,126,133,204,212],"action":[37,53],"policy":[38],"and":[39,123,146,164,202,214],"curiosity":[40,97,145,155,165,179,183],"for":[41,78,142,149],"gain.":[43],"Entropy":[44],"well":[46],"established":[47],"literature,":[50,65],"promoting":[51,66],"randomized":[52],"selection.":[54],"Curiosity":[55],"defined":[57],"a":[59],"broad":[60],"variety":[61],"ways":[63],"discovery":[67],"novel":[69],"experiences.":[70],"One":[71],"example,":[72],"prediction":[73,153,189],"error":[74,154,190],"curiosity,":[75,111],"discovering":[79],"observations":[80],"they":[81],"cannot":[82],"accurately":[83],"predict.":[84],"However,":[85],"such":[86],"may":[88,198],"be":[89],"distracted":[90],"unpredictable":[92],"observational":[93],"noises":[94],"known":[95],"as":[96],"traps.":[98],"Based":[99],"on":[100],"free":[102],"energy":[103],"principle":[104],"(FEP),":[105],"this":[106],"letter":[107],"proposes":[108],"hidden":[109,157,177],"state":[110,158,178],"which":[112,185],"KL":[117],"divergence":[118],"between":[119],"predictive":[121],"prior":[122],"posterior":[124],"probabilities":[125],"latent":[127],"variables.":[128],"We":[129,160],"six":[131],"types":[132],"navigate":[136],"mazes:":[137],"baseline":[138],"without":[140],"or":[144,156],"rewarded":[148],"and/or":[151],"either":[152],"curiosity.":[159,191],"find":[161],"that":[162,197],"result":[166],"exploration,":[169],"especially":[170],"both":[171],"employed":[172],"together.":[173],"Notably,":[174],"with":[176,188],"demonstrate":[180],"resilience":[181],"against":[182],"traps,":[184],"hinder":[186],"This":[192],"suggests":[193],"implementing":[194],"FEP":[196],"enhance":[199],"robustness":[201],"generalization":[203],"models,":[206],"potentially":[207],"aligning":[208],"processes":[211],"biological":[215],"agents.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}