{"id":"https://openalex.org/W2169206416","doi":"https://doi.org/10.1162/neco_a_00600","title":"Risk-Sensitive Reinforcement Learning","display_name":"Risk-Sensitive Reinforcement Learning","publication_year":2014,"publication_date":"2014-04-08","ids":{"openalex":"https://openalex.org/W2169206416","doi":"https://doi.org/10.1162/neco_a_00600","mag":"2169206416","pmid":"https://pubmed.ncbi.nlm.nih.gov/24708369"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_00600","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_00600","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1311.2097","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yun Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yun Shen","raw_affiliation_strings":["Technical University, 10587 Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University, 10587 Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael J. Tobia","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I4210108711","display_name":"University Medical Center Hamburg-Eppendorf","ror":"https://ror.org/01zgy1s35","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael J. Tobia","raw_affiliation_strings":["University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany","institution_ids":["https://openalex.org/I4210108711","https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tobias Sommer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108711","display_name":"University Medical Center Hamburg-Eppendorf","ror":"https://ror.org/01zgy1s35","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I159176309","https://openalex.org/I4210108711"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Sommer","raw_affiliation_strings":["University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany","institution_ids":["https://openalex.org/I4210108711","https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Klaus Obermayer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152641","display_name":"Bernstein Center for Computational Neuroscience Berlin","ror":"https://ror.org/05ewdps05","country_code":"DE","type":"government","lineage":["https://openalex.org/I4210092532","https://openalex.org/I4210152641"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Obermayer","raw_affiliation_strings":["Technical University, 10587 Berlin, Germany, and Bernstein Center for Computational Neuroscience Berlin, 10115 Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University, 10587 Berlin, Germany, and Bernstein Center for Computational Neuroscience Berlin, 10115 Berlin, Germany","institution_ids":["https://openalex.org/I4210152641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":1.7242,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.8405332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"26","issue":"7","first_page":"1298","last_page":"1328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.8980000019073486,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.8980000019073486,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.03449999913573265,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.007300000172108412,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.741599977016449},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4790000021457672},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44200000166893005},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4291999936103821},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4260999858379364},{"id":"https://openalex.org/keywords/prospect-theory","display_name":"Prospect theory","score":0.4187999963760376},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.3763999938964844},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3752000033855438},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.741599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5672000050544739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49000000953674316},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4790000021457672},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4404999911785126},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C339426","wikidata":"https://www.wikidata.org/wiki/Q1151839","display_name":"Prospect theory","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2946000099182129},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2897999882698059},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2535000145435333}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001921","descriptor_name":"Brain","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D001931","descriptor_name":"Brain Mapping","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001931","descriptor_name":"Brain Mapping","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001931","descriptor_name":"Brain Mapping","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D003657","descriptor_name":"Decision Making","qualifier_ui":"Q000502","qualifier_name":"physiology","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":"D008279","descriptor_name":"Magnetic Resonance Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008279","descriptor_name":"Magnetic Resonance Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008279","descriptor_name":"Magnetic Resonance Imaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010100","descriptor_name":"Oxygen","qualifier_ui":"Q000097","qualifier_name":"blood","is_major_topic":false},{"descriptor_ui":"D010100","descriptor_name":"Oxygen","qualifier_ui":"Q000097","qualifier_name":"blood","is_major_topic":false},{"descriptor_ui":"D010100","descriptor_name":"Oxygen","qualifier_ui":"Q000097","qualifier_name":"blood","is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","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":"D012306","descriptor_name":"Risk","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012306","descriptor_name":"Risk","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012306","descriptor_name":"Risk","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017711","descriptor_name":"Nonlinear Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1162/neco_a_00600","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_00600","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:24708369","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24708369","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},{"id":"pmh:oai:arXiv.org:1311.2097","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1311.2097","pdf_url":"https://arxiv.org/pdf/1311.2097","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:1311.2097","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1311.2097","pdf_url":"https://arxiv.org/pdf/1311.2097","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":25,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W617973407","https://openalex.org/W1585575029","https://openalex.org/W1982921646","https://openalex.org/W1998152406","https://openalex.org/W2001009060","https://openalex.org/W2002882646","https://openalex.org/W2017960933","https://openalex.org/W2019291268","https://openalex.org/W2029774518","https://openalex.org/W2033271727","https://openalex.org/W2041946752","https://openalex.org/W2046396733","https://openalex.org/W2068061708","https://openalex.org/W2088135927","https://openalex.org/W2088413745","https://openalex.org/W2107431923","https://openalex.org/W2117726420","https://openalex.org/W2137827713","https://openalex.org/W2139914196","https://openalex.org/W2140282437","https://openalex.org/W2147789157","https://openalex.org/W2334782222","https://openalex.org/W3011865677","https://openalex.org/W4229984434"],"related_works":[],"abstract_inverted_index":{"We":[0,97,143],"derive":[1,98],"a":[2,21,99,120,139,150,184,204],"family":[3],"of":[4,48,66,93,122,127,165,178,187,207],"risk-sensitive":[5,100,147,189,209],"reinforcement":[6],"learning":[7],"methods":[8],"for":[9,79,84,106,124],"agents,":[10],"who":[11],"face":[12],"sequential":[13,140],"decision-making":[14],"tasks":[15],"in":[16,138,196,214],"uncertain":[17],"environments.":[18],"By":[19],"applying":[20],"utility":[22,56],"function":[23],"to":[24,37,43,134,154,162],"the":[25,38,44,49,60,91,125,128,146,155,166,188,197,208,215],"temporal":[26],"difference":[27],"(TD)":[28],"error,":[29],"nonlinear":[30],"transformations":[31],"are":[32,58,113,228],"effectively":[33],"applied":[34],"not":[35,223],"only":[36],"received":[39],"rewards":[40],"but":[41],"also":[42],"true":[45],"transition":[46,111],"probabilities":[47,112],"underlying":[50],"Markov":[51],"decision":[52],"process.":[53],"When":[54],"appropriate":[55],"functions":[57],"chosen,":[59],"agents'":[61],"behaviors":[62],"express":[63],"key":[64],"features":[65],"human":[67,108,136],"behavior":[68,109,137],"as":[69,88,90],"predicted":[70],"by":[71],"prospect":[72,174],"theory":[73],"(Kahneman":[74],"&":[75],"Tversky,":[76],"1979":[77],"),":[78],"example,":[80],"different":[81],"risk":[82],"preferences":[83],"gains":[85],"and":[86,115,158,219],"losses,":[87],"well":[89],"shape":[92],"subjective":[94],"probability":[95],"curves.":[96],"Q-learning":[101],"algorithm,":[102],"which":[103],"is":[104,170,222],"necessary":[105],"modeling":[107],"when":[110],"unknown,":[114],"prove":[116],"its":[117],"convergence.":[118],"As":[119],"proof":[121],"principle":[123],"applicability":[126],"new":[129],"framework,":[130],"we":[131,202],"apply":[132],"it":[133,160],"quantify":[135],"investment":[141],"task.":[142],"find":[144,203],"that":[145,159,169,221],"variant":[148],"provides":[149],"significantly":[151],"better":[152],"fit":[153],"behavioral":[156],"data":[157],"leads":[161],"an":[163],"interpretation":[164],"subject's":[167],"responses":[168],"indeed":[171],"consistent":[172],"with":[173,192,211],"theory.":[175],"The":[176],"analysis":[177],"simultaneously":[179],"measured":[180],"fMRI":[181],"signals":[182],"shows":[183],"significant":[185,205],"correlation":[186,206],"TD":[190],"error":[191],"BOLD":[193],"signal":[194],"change":[195],"ventral":[198],"striatum.":[199],"In":[200],"addition":[201],"Q-values":[210,227],"neural":[212],"activity":[213],"striatum,":[216],"cingulate":[217],"cortex,":[218],"insula":[220],"present":[224],"if":[225],"standard":[226],"used.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2016-06-24T00:00:00"}