{"id":"https://openalex.org/W6983482956","doi":null,"title":"Meta-learning emotional control in bandit tasks","display_name":"Meta-learning emotional control in bandit tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6983482956"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt7xr3j96w","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7xr3j96w","pdf_url":"https://escholarship.org/content/qt7xr3j96w/qt7xr3j96w.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 46, iss 0","raw_type":"article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt7xr3j96w/qt7xr3j96w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051980333","display_name":"Prakhar Godara","orcid":"https://orcid.org/0000-0003-4867-8542","observed_orcids":["https://orcid.org/0000-0003-4867-8542"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Godara, Prakhar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051980333"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37088234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9839000105857849,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9839000105857849,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.006500000134110451,"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":0.004999999888241291,"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/meta-reasoning","display_name":"meta-reasoning","score":0.9539999961853027},{"id":"https://openalex.org/keywords/emotional-control","display_name":"emotional control","score":0.7919999957084656},{"id":"https://openalex.org/keywords/two-armed-bandit","display_name":"two-armed bandit","score":0.7160000205039978},{"id":"https://openalex.org/keywords/unknown-environments","display_name":"unknown environments","score":0.5960000157356262},{"id":"https://openalex.org/keywords/human-exploration","display_name":"human exploration","score":0.5270000100135803},{"id":"https://openalex.org/keywords/decision-making","display_name":"decision-making","score":0.6600000262260437}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6532999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698999762535095},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5062000155448914},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3815999925136566},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C31772880","wikidata":"https://www.wikidata.org/wiki/Q2666479","display_name":"Rational agent","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C64431516","wikidata":"https://www.wikidata.org/wiki/Q5249235","display_name":"Decision field theory","level":5,"score":0.26179999113082886},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt7xr3j96w","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7xr3j96w","pdf_url":"https://escholarship.org/content/qt7xr3j96w/qt7xr3j96w.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 46, iss 0","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt7xr3j96w","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/7xr3j96w","pdf_url":"https://escholarship.org/content/qt7xr3j96w/qt7xr3j96w.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 46, iss 0","raw_type":"article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6983482956.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4406301929","https://openalex.org/W6990799627","https://openalex.org/W3027608700","https://openalex.org/W2543472697","https://openalex.org/W2129384778","https://openalex.org/W3126935522","https://openalex.org/W4213360688","https://openalex.org/W2978450277","https://openalex.org/W7133185682","https://openalex.org/W2940726987"],"abstract_inverted_index":{"In":[0],"decision":[1,87],"making":[2,116],"scenarios,":[3],"reasoning":[4],"can":[5],"be":[6],"viewed":[7],"as":[8,81],"an":[9,12,19],"agent":[10],"executing":[11],"algorithm":[13],"p":[14,34],"\u201a\u00e0\u00e0":[15,22],"P":[16],"that":[17,49],"selects":[18],"action":[20],"a":[21,37,82,129],"A,":[23],"aiming":[24],"to":[25,42,67],"optimize":[26],"some":[27],"outcome.":[28],"Metareasoning":[29],"extends":[30],"this":[31,97],"by":[32,55,76],"selecting":[33],"itself":[35],"through":[36],"meta-algorithm":[38],"p^{meta}.":[39],"Previous":[40],"approaches":[41],"study":[43,68],"metareasoning":[44,69,120],"in":[45,73,115,136],"humans":[46],"have":[47],"required":[48],"the":[50,56,59,78,93,100,117],"transition/reward":[51],"distributions":[52],"are":[53],"known":[54],"agent,":[57],"but":[58,123],"value":[60],"function":[61],"isn't.":[62],"We":[63,90],"extend":[64],"these":[65],"efforts":[66],"for":[70,128],"agents":[71],"acting":[72],"unknown":[74],"environments":[75],"formalizing":[77],"meta":[79,83],"problem":[80,88,121],"Bayes":[84],"adaptive":[85],"Markov":[86],"(meta-BAMDP).":[89],"formally":[91],"investigate":[92],"theoretical":[94,113],"consequences":[95],"of":[96,102,133],"framework":[98],"within":[99],"context":[101],"two-armed":[103],"Bernoulli":[104],"bandit":[105],"(TABB)":[106],"tasks.":[107,138],"Not":[108],"only":[109],"do":[110],"we":[111,124],"make":[112],"progress":[114],"(usually":[118],"intractable)":[119],"tractable,":[122],"also":[125],"generate":[126],"predictions":[127],"resource":[130],"rational":[131],"account":[132],"human":[134],"exploration":[135],"TABB":[137]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}