{"id":"https://openalex.org/W3092740831","doi":"https://doi.org/10.1371/journal.pcbi.1008317","title":"Reward-predictive representations generalize across tasks in reinforcement learning","display_name":"Reward-predictive representations generalize across tasks in reinforcement learning","publication_year":2020,"publication_date":"2020-10-15","ids":{"openalex":"https://openalex.org/W3092740831","doi":"https://doi.org/10.1371/journal.pcbi.1008317","mag":"3092740831","pmid":"https://pubmed.ncbi.nlm.nih.gov/33057329"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1008317","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1008317","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1008317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006414380","display_name":"Lucas Lehnert","orcid":"https://orcid.org/0000-0001-5897-499X"},"institutions":[{"id":"https://openalex.org/I1314596251","display_name":"Allen Institute for Brain Science","ror":"https://ror.org/00dcv1019","country_code":"US","type":"facility","lineage":["https://openalex.org/I1314596251","https://openalex.org/I4210140341"]},{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lucas Lehnert","raw_affiliation_strings":["Carney Institute for Brain Science, Brown University, Providence, RI 02912, USA","Computer Science Department, Brown University, Providence, RI 02912, USA"],"raw_orcid":"https://orcid.org/0000-0001-5897-499X","affiliations":[{"raw_affiliation_string":"Carney Institute for Brain Science, Brown University, Providence, RI 02912, USA","institution_ids":["https://openalex.org/I27804330","https://openalex.org/I1314596251"]},{"raw_affiliation_string":"Computer Science Department, Brown University, Providence, RI 02912, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Computer Science Department, Brown University, Providence, RI 02912, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brown University, Providence, RI 02912, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007609257","display_name":"Michael J. Frank","orcid":"https://orcid.org/0000-0001-8451-0523"},"institutions":[{"id":"https://openalex.org/I1314596251","display_name":"Allen Institute for Brain Science","ror":"https://ror.org/00dcv1019","country_code":"US","type":"facility","lineage":["https://openalex.org/I1314596251","https://openalex.org/I4210140341"]},{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Frank","raw_affiliation_strings":["Carney Institute for Brain Science, Brown University, Providence, RI 02912, USA","Department of Cognitive, Linguistic & Psychological Sciences, Brown University, Providence, RI 02912, USA"],"raw_orcid":"https://orcid.org/0000-0001-8451-0523","affiliations":[{"raw_affiliation_string":"Carney Institute for Brain Science, Brown University, Providence, RI 02912, USA","institution_ids":["https://openalex.org/I27804330","https://openalex.org/I1314596251"]},{"raw_affiliation_string":"Department of Cognitive, Linguistic & Psychological Sciences, Brown University, Providence, RI 02912, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006414380"],"corresponding_institution_ids":["https://openalex.org/I1314596251","https://openalex.org/I27804330"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":2.6151,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.90384317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"10","first_page":"e1008317","last_page":"e1008317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9977999925613403,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9977999925613403,"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":0.9976999759674072,"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":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7949302792549133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062642574310303},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6701353788375854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5762189626693726},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5672706961631775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222328901290894},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4651888906955719},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4508235454559326},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.44775480031967163},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4397006034851074},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.41375795006752014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37539851665496826},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.26460617780685425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09577533602714539}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7949302792549133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062642574310303},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6701353788375854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5762189626693726},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5672706961631775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222328901290894},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4651888906955719},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4508235454559326},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.44775480031967163},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4397006034851074},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.41375795006752014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37539851665496826},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26460617780685425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09577533602714539},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"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":"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":"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":"D006801","descriptor_name":"Humans","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":"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":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","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":"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":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013647","descriptor_name":"Task Performance and Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013647","descriptor_name":"Task Performance and Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013647","descriptor_name":"Task Performance and Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013647","descriptor_name":"Task Performance and Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013647","descriptor_name":"Task Performance and Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1371/journal.pcbi.1008317","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1008317","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:33057329","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33057329","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:RePEc:plo:pcbi00:1008317","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1008317","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:c974a410c9fe40b3afcec3ba2be17a91","is_oa":true,"landing_page_url":"https://doaj.org/article/c974a410c9fe40b3afcec3ba2be17a91","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 16, Iss 10, p e1008317 (2020)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:6537415","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC7591094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7591094","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7591094","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1008317","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1008317","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G3423266768","display_name":null,"funder_award_id":"T32MH115895","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5633974728","display_name":null,"funder_award_id":"MH084840","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1491843047","https://openalex.org/W1539216098","https://openalex.org/W1557517019","https://openalex.org/W1652173018","https://openalex.org/W1875347116","https://openalex.org/W1982670892","https://openalex.org/W1995688924","https://openalex.org/W2056354534","https://openalex.org/W2058735307","https://openalex.org/W2097381042","https://openalex.org/W2115870554","https://openalex.org/W2119259385","https://openalex.org/W2119567691","https://openalex.org/W2119842714","https://openalex.org/W2121863487","https://openalex.org/W2136820623","https://openalex.org/W2140956413","https://openalex.org/W2145339207","https://openalex.org/W2153983642","https://openalex.org/W2154262526","https://openalex.org/W2158266063","https://openalex.org/W2161966552","https://openalex.org/W2191938486","https://openalex.org/W2334782222","https://openalex.org/W2341634245","https://openalex.org/W2397240726","https://openalex.org/W2405468764","https://openalex.org/W2417089653","https://openalex.org/W2440926996","https://openalex.org/W2507425266","https://openalex.org/W2522716651","https://openalex.org/W2591012103","https://openalex.org/W2604220916","https://openalex.org/W2609154042","https://openalex.org/W2742143911","https://openalex.org/W2752853835","https://openalex.org/W2803178532","https://openalex.org/W2804040390","https://openalex.org/W2804673281","https://openalex.org/W2854445389","https://openalex.org/W2904339729","https://openalex.org/W2911989133","https://openalex.org/W2950347959","https://openalex.org/W2951066214","https://openalex.org/W2952504784","https://openalex.org/W2952509347","https://openalex.org/W2952705521","https://openalex.org/W2953319434","https://openalex.org/W2954020015","https://openalex.org/W2955321733","https://openalex.org/W2962717849","https://openalex.org/W2963019567","https://openalex.org/W2963488340","https://openalex.org/W2969743374","https://openalex.org/W2972967522","https://openalex.org/W2990138404","https://openalex.org/W2990858845","https://openalex.org/W2994987910","https://openalex.org/W3099111597","https://openalex.org/W3103493959","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6712173889"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W4225571923"],"abstract_inverted_index":{"In":[0],"computer":[1],"science,":[2],"reinforcement":[3],"learning":[4],"is":[5,87,184],"a":[6,152,155],"powerful":[7],"framework":[8],"with":[9,33,138,199,208],"which":[10,79],"artificial":[11],"agents":[12],"can":[13],"learn":[14],"to":[15,60,76,89,118,187,228],"maximize":[16,214],"their":[17,58],"performance":[18,39],"for":[19],"any":[20,217],"given":[21,218],"Markov":[22],"decision":[23],"process":[24],"(MDP).":[25],"Advances":[26],"over":[27,41],"the":[28,80,84,148,169,180,188],"last":[29],"decade,":[30],"in":[31,43,57,78,130,165,216,224,236],"combination":[32],"deep":[34],"neural":[35,231],"networks,":[36],"have":[37],"enjoyed":[38],"advantages":[40],"humans":[42,225],"many":[44],"difficult":[45],"task":[46,153],"settings.":[47],"However,":[48],"such":[49,243],"frameworks":[50],"perform":[51,239],"far":[52],"less":[53],"favorably":[54],"when":[55],"evaluated":[56],"ability":[59],"generalize":[61,135],"or":[62,83],"transfer":[63,72,104],"representations":[64,117,146],"across":[65,136,197],"different":[66,139,200],"tasks.":[67,121],"Existing":[68],"algorithms":[69],"that":[70,110,125,127,162,212,241],"facilitate":[71,242],"typically":[73,105],"are":[74,163,178],"limited":[75],"cases":[77],"transition":[81,140,170,189,203],"function":[82],"optimal":[85],"policy":[86],"portable":[88],"new":[90],"contexts,":[91],"but":[92],"achieving":[93],"\"deep":[94],"transfer\"":[95],"characteristic":[96],"of":[97,108,114,132,151,167],"human":[98],"behavior":[99],"has":[100],"been":[101],"elusive.":[102],"Such":[103,144],"requires":[106],"discovery":[107],"abstractions":[109,126,211,240],"permit":[111],"analogical":[112],"reuse":[113],"previously":[115],"learned":[116],"superficially":[119],"distinct":[120],"Here,":[122],"we":[123],"demonstrate":[124],"minimize":[128],"error":[129],"predictions":[131],"reward":[133,142,172,191,201,215],"outcomes":[134],"tasks":[137,198],"and":[141,171,190,194,202,220,226,232],"functions.":[143,173,204],"reward-predictive":[145],"compress":[147],"state":[149,176,182,237],"space":[150],"into":[154],"lower":[156],"dimensional":[157],"representation":[158,183,238],"by":[159],"combining":[160],"states":[161],"equivalent":[164],"terms":[166],"both":[168],"Because":[174],"only":[175],"equivalences":[177],"considered,":[179],"resulting":[181],"not":[185],"tied":[186],"functions":[192],"themselves":[193],"thus":[195],"generalizes":[196],"These":[205],"results":[206],"contrast":[207],"those":[209],"using":[210],"myopically":[213],"MDP":[219],"motivate":[221],"further":[222],"experiments":[223],"animals":[227],"investigate":[229],"if":[230],"cognitive":[233],"systems":[234],"involved":[235],"equivalence":[244],"relations.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}
