{"id":"https://openalex.org/W4386778772","doi":"https://doi.org/10.1177/10597123231201655","title":"Combining imitation and deep reinforcement learning to human-level performance on a virtual foraging task","display_name":"Combining imitation and deep reinforcement learning to human-level performance on a virtual foraging task","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386778772","doi":"https://doi.org/10.1177/10597123231201655"},"language":"en","primary_location":{"id":"doi:10.1177/10597123231201655","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10597123231201655","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5075631895","display_name":"Vittorio Giammarino","orcid":"https://orcid.org/0000-0001-7082-3262"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vittorio Giammarino","raw_affiliation_strings":["Division of Systems Engineering, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Division of Systems Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007634388","display_name":"Matthew F Dunne","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew F Dunne","raw_affiliation_strings":["Center for Systems Neuroscience, Boston University, Boston, MA, USA","Cognitive Neuroimaging Center, Boston University, Boston, MA, USA","Graduate Program for Neuroscience, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Systems Neuroscience, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Cognitive Neuroimaging Center, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Graduate Program for Neuroscience, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055789758","display_name":"Kylie N Moore","orcid":"https://orcid.org/0000-0001-8947-2829"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kylie N Moore","raw_affiliation_strings":["Center for Systems Neuroscience, Boston University, Boston, MA, USA","Cognitive Neuroimaging Center, Boston University, Boston, MA, USA","Graduate Program for Neuroscience, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Systems Neuroscience, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Cognitive Neuroimaging Center, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Graduate Program for Neuroscience, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088108309","display_name":"Michael E. Hasselmo","orcid":"https://orcid.org/0000-0002-9925-6377"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E Hasselmo","raw_affiliation_strings":["Center for Systems Neuroscience, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Systems Neuroscience, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090312031","display_name":"Chantal E. Stern","orcid":"https://orcid.org/0000-0003-1280-6717"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chantal E Stern","raw_affiliation_strings":["Cognitive Neuroimaging Center, Boston University, Boston, MA, USA","Graduate Program for Neuroscience, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Neuroimaging Center, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Graduate Program for Neuroscience, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075696701","display_name":"Ioannis Ch. Paschalidis","orcid":"https://orcid.org/0000-0002-3343-2913"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ioannis Ch Paschalidis","raw_affiliation_strings":["Department of Biomedical Engineering, Boston University, Boston, MA, USA","Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA","Division of Systems Engineering, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Division of Systems Engineering, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075631895"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":0.5254,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71646637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"3","first_page":"251","last_page":"263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10581","display_name":"Neural dynamics and brain function","score":0.95169997215271,"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/T11431","display_name":"Action Observation and Synchronization","score":0.9438999891281128,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586908340454102},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7318569421768188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7229965329170227},{"id":"https://openalex.org/keywords/foraging","display_name":"Foraging","score":0.6257168650627136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6159747838973999},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.573591411113739},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.543912947177887},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.521503746509552},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.46449756622314453},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2597687840461731},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10723623633384705},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0906795859336853},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.073557049036026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586908340454102},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7318569421768188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7229965329170227},{"id":"https://openalex.org/C165287380","wikidata":"https://www.wikidata.org/wiki/Q2916569","display_name":"Foraging","level":2,"score":0.6257168650627136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6159747838973999},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.573591411113739},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.543912947177887},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.521503746509552},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.46449756622314453},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2597687840461731},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10723623633384705},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0906795859336853},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.073557049036026},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10597123231201655","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10597123231201655","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G700747938","display_name":null,"funder_award_id":"N00014-17-1-2304","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"}],"funders":[{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1483373940","https://openalex.org/W1931877416","https://openalex.org/W1973898841","https://openalex.org/W1988745641","https://openalex.org/W1999874108","https://openalex.org/W2006583031","https://openalex.org/W2018174473","https://openalex.org/W2051228319","https://openalex.org/W2098774185","https://openalex.org/W2132880990","https://openalex.org/W2134491302","https://openalex.org/W2147347966","https://openalex.org/W2166302491","https://openalex.org/W2169498096","https://openalex.org/W2290104316","https://openalex.org/W2396952885","https://openalex.org/W2415726935","https://openalex.org/W2559655401","https://openalex.org/W2596585349","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2788862220","https://openalex.org/W2938321354","https://openalex.org/W2963099939","https://openalex.org/W2963411833","https://openalex.org/W2963841869","https://openalex.org/W2988072049","https://openalex.org/W3007827511","https://openalex.org/W3022566517","https://openalex.org/W3032398409","https://openalex.org/W3035700320","https://openalex.org/W3038892247","https://openalex.org/W3082040901","https://openalex.org/W3096831136","https://openalex.org/W3177232011","https://openalex.org/W3196807373","https://openalex.org/W4225495521","https://openalex.org/W4288363736","https://openalex.org/W4289258965","https://openalex.org/W4297664295","https://openalex.org/W4298857966","https://openalex.org/W6638018090","https://openalex.org/W6680724558","https://openalex.org/W6751285671"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"We":[0,12,83,117,145],"develop":[1],"a":[2],"framework":[3,42],"to":[4,30,45,62,71,141,153],"learn":[5],"bio-inspired":[6],"foraging":[7,25],"policies":[8,88,113],"using":[9,93],"human":[10,48,69,127],"data.":[11],"conduct":[13],"an":[14,22,164],"experiment":[15],"where":[16],"humans":[17],"are":[18,28],"virtually":[19],"immersed":[20],"in":[21],"open":[23],"field":[24],"environment":[26],"and":[27,108,124,129,151],"trained":[29,134],"collect":[31],"the":[32,47,86,94,112,120,131,168],"highest":[33],"amount":[34],"of":[35,122,167],"rewards.":[36],"A":[37],"Markov":[38],"Decision":[39],"Process":[40],"(MDP)":[41],"is":[43,60],"introduced":[44],"model":[46],"decision":[49],"dynamics.":[50],"Then,":[51],"Imitation":[52],"Learning":[53,91],"(IL)":[54],"based":[55],"on":[56,159],"maximum":[57],"likelihood":[58],"estimation":[59],"used":[61],"train":[63],"Neural":[64],"Networks":[65],"(NN)":[66],"that":[67,77,119,130,148],"map":[68],"decisions":[70],"observed":[72],"states.":[73],"The":[74],"results":[75],"show":[76,118,147],"passive":[78],"imitation":[79],"substantially":[80],"underperforms":[81],"humans.":[82],"further":[84],"refine":[85],"human-inspired":[87],"via":[89],"Reinforcement":[90],"(RL)":[92],"on-policy":[95],"Proximal":[96],"Policy":[97],"Optimization":[98],"(PPO)":[99],"algorithm":[100],"which":[101],"shows":[102],"better":[103],"stability":[104],"than":[105],"other":[106],"algorithms":[107],"can":[109,138],"steadily":[110],"improve":[111],"pre-trained":[114],"with":[115,135,163],"IL.":[116],"combination":[121],"IL":[123],"RL":[125],"match":[126],"performance":[128,150],"artificial":[132],"agents":[133],"our":[136],"approach":[137],"quickly":[139],"adapt":[140],"reward":[142,154],"distribution":[143,155],"shift.":[144],"finally":[146],"good":[149],"robustness":[152],"shift":[156],"strongly":[157],"depend":[158],"combining":[160],"allocentric":[161],"information":[162],"egocentric":[165],"representation":[166],"environment.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}