{"id":"https://openalex.org/W2941635866","doi":null,"title":"Shaping Model-Free Habits with Model-Based Goals.","display_name":"Shaping Model-Free Habits with Model-Based Goals.","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2941635866","mag":"2941635866"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt8sd7s177","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8sd7s177","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 40, iss 0","raw_type":"article"},"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/A5086558424","display_name":"Paul M. Krueger","orcid":"https://orcid.org/0000-0001-5698-8984","observed_orcids":["https://orcid.org/0000-0001-5698-8984"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul M. Krueger","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5698-8984","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077079119","display_name":"Thomas L. Griffiths","orcid":"https://orcid.org/0000-0002-5138-7255","observed_orcids":["https://orcid.org/0000-0002-5138-7255","https://orcid.org/0000-0002-1542-8128","https://orcid.org/0000-0002-1317-7038","https://orcid.org/0000-0001-7820-6787"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Griffiths","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1542-8128","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2417,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58516662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.00019999999494757503,"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/T10056","display_name":"Neurotransmitter Receptor Influence on Behavior","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.8339999914169312},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"dynamic programming","score":0.7889999747276306},{"id":"https://openalex.org/keywords/optimal-policy","display_name":"optimal policy","score":0.574999988079071},{"id":"https://openalex.org/keywords/human-learning","display_name":"human learning","score":0.3319999873638153},{"id":"https://openalex.org/keywords/moral-emotions","display_name":"moral emotions","score":0.8119999766349792},{"id":"https://openalex.org/keywords/innate-behavior","display_name":"innate behavior","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4986391067504883},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32711243629455566}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt8sd7s177","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/8sd7s177","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Annual Meeting of the Cognitive Science Society, vol 40, iss 0","raw_type":"article"},{"id":"mag:2941635866","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/cogsci/cogsci2018.html#KruegerG18","pdf_url":null,"source":{"id":"https://openalex.org/S78735424","display_name":"Cognitive Science","issn_l":"0364-0213","issn":["0364-0213","1551-6709"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-2","ki-jl-2","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Cognitive Science","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":23,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W1967987271","https://openalex.org/W1980035368","https://openalex.org/W1980744233","https://openalex.org/W1988699227","https://openalex.org/W1990005421","https://openalex.org/W2000214310","https://openalex.org/W2004526332","https://openalex.org/W2009533501","https://openalex.org/W2046194382","https://openalex.org/W2048226872","https://openalex.org/W2086282937","https://openalex.org/W2107525024","https://openalex.org/W2111535985","https://openalex.org/W2116708838","https://openalex.org/W2121863487","https://openalex.org/W2125252313","https://openalex.org/W2149565728","https://openalex.org/W2149892666","https://openalex.org/W2153894094","https://openalex.org/W2167362547","https://openalex.org/W2169323873","https://openalex.org/W2949941589"],"related_works":["https://openalex.org/W7052802116","https://openalex.org/W3132265590","https://openalex.org/W2756350131","https://openalex.org/W4391325403","https://openalex.org/W2548153745","https://openalex.org/W4293198207","https://openalex.org/W3120276360","https://openalex.org/W4408815420","https://openalex.org/W4386534373","https://openalex.org/W7062726074"],"abstract_inverted_index":{"Model-free":[0],"(MF)":[1],"and":[2,18,61,163],"model-based":[3],"(MB)":[4],"reinforcement":[5],"learn-ing":[6],"(RL)":[7],"have":[8],"provided":[9],"a":[10,43,82,127,131,156,174],"successful":[11],"framework":[12],"for":[13,29,179],"under-standing":[14],"both":[15],"human":[16,66],"behavior":[17],"neural":[19],"data.":[20],"These":[21],"two":[22],"sys-tems":[23],"are":[24,115],"usually":[25],"thought":[26],"to":[27,56,98,106,121,136,159],"compete":[28],"control":[30],"of":[31,53,91,126,169,176],"behavior.However,":[32],"it":[33,185],"has":[34],"also":[35,154],"been":[36],"proposed":[37],"that":[38,76,103,166,184,189],"they":[39],"can":[40],"be":[41],"integratedin":[42],"cooperative":[44],"manner.":[45],"For":[46],"example,":[47],"the":[48,58,86,92,107,111,123,138,170,187],"Dyna":[49,149],"algorithm":[50],"usesMB":[51],"replay":[52],"past":[54],"experience":[55,178],"train":[57],"MF":[59,128,162],"system,":[60],"hasinspired":[62],"research":[63],"examining":[64],"whether":[65],"learners":[67],"do":[68],"some-thing":[69],"similar.":[70],"Here":[71],"we":[72],"introduce":[73],"an":[74],"approach":[75],"links":[77],"MFand":[78],"MB":[79,164],"learning":[80,93],"in":[81,130],"new":[83,157],"way:":[84],"via":[85],"reward":[87,124],"function.":[88],"Givena":[89],"model":[90],"environment,":[94],"dynamic":[95],"programmingis":[96],"used":[97],"iteratively":[99],"approximate":[100],"state":[101,108],"values":[102,109,119],"monotoni-cally":[104],"converge":[105],"under":[110],"optimal":[112,139],"decisionpolicy.":[113],"Pseudorewards":[114],"calculated":[116],"from":[117],"these":[118],"andused":[120],"shape":[122],"function":[125],"learner":[129],"waythat":[132],"is":[133],"guaranteed":[134],"not":[135],"change":[137],"policy.":[140],"We":[141,194],"showthat":[142],"this":[143],"method":[144],"offers":[145,155],"computational":[146],"advantages":[147],"over":[148],"intwo":[150],"classic":[151],"problems.":[152],"It":[153],"way":[158],"think":[160],"aboutintegrating":[161],"RL:":[165],"our":[167,181],"knowledge":[168],"worlddoesn\u2019t":[171],"just":[172],"provide":[173],"source":[175],"simulated":[177],"train-ing":[180],"instincts,":[182],"but":[183],"shapes":[186],"rewards":[188],"those":[190],"in-stincts":[191],"latch":[192],"onto.":[193],"discuss":[195],"psychological":[196],"phenomena":[197],"thatthis":[198],"theory":[199],"could":[200],"apply":[201],"to,":[202],"including":[203],"moral":[204],"emotions.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-05-03T00:00:00"}