{"id":"https://openalex.org/W4414162375","doi":"https://doi.org/10.1371/journal.pcbi.1013454","title":"Adaptive algorithms for shaping behavior","display_name":"Adaptive algorithms for shaping behavior","publication_year":2025,"publication_date":"2025-09-12","ids":{"openalex":"https://openalex.org/W4414162375","doi":"https://doi.org/10.1371/journal.pcbi.1013454","pmid":"https://pubmed.ncbi.nlm.nih.gov/40939015"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1013454","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013454","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.1013454","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080017321","display_name":"William L. Tong","orcid":"https://orcid.org/0000-0003-4319-4303"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William L. Tong","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts, United States of America","The Kempner Institute for the Study of Natural and Artificial Intelligence, Allston, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"The Kempner Institute for the Study of Natural and Artificial Intelligence, Allston, Massachusetts, United States of America","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071055922","display_name":"Venkatesh N. Murthy","orcid":"https://orcid.org/0000-0003-2443-4252"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Venkatesh N. Murthy","raw_affiliation_strings":["Center for Brain Science, Harvard University, Cambridge, Massachusetts, United States of America","Department of Molecular and Cellular Biology, Harvard University, Cambridge, Massachusetts, United States of America","The Kempner Institute for the Study of Natural and Artificial Intelligence, Allston, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2443-4252","affiliations":[{"raw_affiliation_string":"Center for Brain Science, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Molecular and Cellular Biology, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"The Kempner Institute for the Study of Natural and Artificial Intelligence, Allston, Massachusetts, United States of America","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046720392","display_name":"Gautam Reddy","orcid":"https://orcid.org/0000-0002-1276-9613"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210133539","display_name":"3D Technology Laboratories (United States)","ror":"https://ror.org/03fffdr10","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133539"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gautam Reddy","raw_affiliation_strings":["Center for Brain Science, Harvard University, Cambridge, Massachusetts, United States of America","Joseph Henry Laboratories of Physics, Princeton University, Princeton, New Jersey, United States of America","Physics and Informatics Laboratories, NTT Research, Inc., Sunnyvale, California, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-1276-9613","affiliations":[{"raw_affiliation_string":"Center for Brain Science, Harvard University, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Joseph Henry Laboratories of Physics, Princeton University, Princeton, New Jersey, United States of America","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Physics and Informatics Laboratories, NTT Research, Inc., Sunnyvale, California, United States of America","institution_ids":["https://openalex.org/I4210133539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046720392","https://openalex.org/A5071055922","https://openalex.org/A5080017321"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I20089843","https://openalex.org/I4210133539","https://openalex.org/I4210156221"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11643664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"9","first_page":"e1013454","last_page":"e1013454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9966999888420105,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9966999888420105,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9886000156402588,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.979200005531311,"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":0.7024999856948853},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6276999711990356},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.6019999980926514},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5873000025749207},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4754999876022339},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4341999888420105},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43369999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268000245094299},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7024999856948853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722000002861023},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.25540000200271606}],"mesh":[{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive 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":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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D001522","descriptor_name":"Behavior, Animal","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D001522","descriptor_name":"Behavior, Animal","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D001522","descriptor_name":"Behavior, Animal","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D001522","descriptor_name":"Behavior, Animal","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D004285","descriptor_name":"Dogs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004285","descriptor_name":"Dogs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004285","descriptor_name":"Dogs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004285","descriptor_name":"Dogs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","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":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","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":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1013454","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013454","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:40939015","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40939015","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:doaj.org/article:2e7f62b4d41f4a9d8d5f625eea0e0851","is_oa":true,"landing_page_url":"https://doaj.org/article/2e7f62b4d41f4a9d8d5f625eea0e0851","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"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 21, Iss 9, p e1013454 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11258374","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12448964","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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12448964","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12448964/","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.1013454","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1013454","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":[],"awards":[{"id":"https://openalex.org/G3524007437","display_name":null,"funder_award_id":"A47994","funder_id":"https://openalex.org/F5876947149","funder_display_name":"NTT Research"},{"id":"https://openalex.org/G4465099768","display_name":null,"funder_award_id":"R01DC017311","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5642881205","display_name":null,"funder_award_id":"RF1NS128865","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/F5876947149","display_name":"NTT Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1902261929","https://openalex.org/W1970616645","https://openalex.org/W1977906889","https://openalex.org/W2007347635","https://openalex.org/W2011418219","https://openalex.org/W2044375425","https://openalex.org/W2046695302","https://openalex.org/W2076168055","https://openalex.org/W2083803136","https://openalex.org/W2097144131","https://openalex.org/W2101524054","https://openalex.org/W2112862259","https://openalex.org/W2126316555","https://openalex.org/W2129292615","https://openalex.org/W2139612737","https://openalex.org/W2151834591","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2296073425","https://openalex.org/W2527978657","https://openalex.org/W2951975928","https://openalex.org/W2963099939","https://openalex.org/W2963276097","https://openalex.org/W2968917487","https://openalex.org/W2972758308","https://openalex.org/W2988893955","https://openalex.org/W3011124693","https://openalex.org/W3040707741","https://openalex.org/W3095669803","https://openalex.org/W3162611316","https://openalex.org/W3214094424","https://openalex.org/W4220747123","https://openalex.org/W4226500654","https://openalex.org/W4246515624","https://openalex.org/W4281385971","https://openalex.org/W4310102427"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Dogs":[0],"and":[1,54,80,92,118,158],"laboratory":[2],"mice":[3],"are":[4,22,137],"commonly":[5],"trained":[6],"to":[7,87,134,155],"perform":[8],"complex":[9],"tasks":[10,19,127],"by":[11],"guiding":[12],"them":[13],"through":[14],"a":[15,32,75,114,142,146],"curriculum":[16],"of":[17,52],"simpler":[18,91],"('shaping').":[20],"What":[21],"the":[23,49],"principles":[24],"behind":[25],"effective":[26],"shaping":[27,36,72,103,151],"strategies?":[28],"Here,":[29],"we":[30,68,99,109],"propose":[31],"teacher-student":[33],"framework":[34,149],"for":[35,62,150],"behavior,":[37],"where":[38],"an":[39,101],"autonomous":[40],"teacher":[41],"agent":[42],"decides":[43],"its":[44],"student's":[45,50],"task":[46,117],"based":[47],"on":[48,56,96,113,125],"transcript":[51],"successes":[53],"failures":[55],"previously":[57],"assigned":[58],"tasks.":[59,94],"Using":[60],"algorithms":[61,73,83],"Monte":[63],"Carlo":[64],"planning":[65],"under":[66],"uncertainty,":[67],"show":[69,110],"that":[70,128,153],"near-optimal":[71,112],"achieve":[74],"careful":[76],"balance":[77],"between":[78,90],"reinforcement":[79,122],"extinction.":[81],"Near-optimal":[82],"track":[84],"learning":[85,116,123],"rate":[86],"adaptively":[88],"alternate":[89],"harder":[93],"Based":[95],"this":[97],"intuition,":[98],"derive":[100],"adaptive":[102],"heuristic":[104],"with":[105],"minimal":[106],"parameters,":[107],"which":[108],"is":[111],"sequence":[115],"robustly":[119],"trains":[120],"deep":[121],"agents":[124],"navigation":[126],"involve":[129],"sparse,":[130],"delayed":[131],"rewards.":[132],"Extensions":[133],"continuous":[135],"curricula":[136],"explored.":[138],"Our":[139],"work":[140],"provides":[141],"starting":[143],"point":[144],"towards":[145],"general":[147],"computational":[148],"behavior":[152],"applies":[154],"both":[156],"animals":[157],"artificial":[159],"agents.":[160]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}