{"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","doi":"https://doi.org/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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-1","ki-jl-1","norway-1","poland-40","russia-white-list-2","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.06250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075631895","display_name":"Vittorio Giammarino","orcid":"https://orcid.org/0000-0001-7082-3262","observed_orcids":["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"],"raw_orcid":"https://orcid.org/0000-0001-7082-3262","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,"observed_orcids":[]},"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"],"raw_orcid":null,"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","observed_orcids":["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"],"raw_orcid":null,"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 Erik Hasselmo","orcid":"https://orcid.org/0000-0002-9925-6377","observed_orcids":["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"],"raw_orcid":null,"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","observed_orcids":["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"],"raw_orcid":null,"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","observed_orcids":["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"],"raw_orcid":null,"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":1,"corresponding_author_ids":["https://openalex.org/A5075631895"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":{"value":3750,"currency":"USD","value_usd":3750},"apc_paid":null,"fwci":0.345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56283906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/imitation-learning","display_name":"imitation learning","score":0.7049999833106995},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9769999980926514},{"id":"https://openalex.org/keywords/foraging-behavior","display_name":"foraging behavior","score":0.859000027179718},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9259999990463257},{"id":"https://openalex.org/keywords/maximum-likelihood-estimation","display_name":"maximum likelihood estimation","score":0.7279999852180481},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9269999861717224},{"id":"https://openalex.org/keywords/allocentric-representation","display_name":"allocentric spatial representation","score":0.9179999828338623},{"id":"https://openalex.org/keywords/egocentric-representation","display_name":"egocentric representation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/human-level-performance","display_name":"human-level performance","score":0.5009999871253967}],"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":3,"locations":[{"id":"doi:10.1177/10597123231201655","doi":"https://doi.org/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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-1","ki-jl-1","norway-1","poland-40","russia-white-list-2","vabb-shw"],"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"},{"id":"pmh:oai:arXiv.org:2203.06250","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.06250","pdf_url":"https://arxiv.org/pdf/2203.06250","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2203.06250","doi":"https://doi.org/10.48550/arxiv.2203.06250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.06250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.06250","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.06250","pdf_url":"https://arxiv.org/pdf/2203.06250","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1908768498","display_name":null,"funder_award_id":"N00014-21-1-2844","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2302785604","display_name":"Functional Organization of Navigational Coding in the Human Brain","funder_award_id":"1829398","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2753468595","display_name":"CPS: Breakthrough: A Dynamic Optimization Framework for Connected Automated Vehicles in Urban Environments","funder_award_id":"1645681","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2770765901","display_name":null,"funder_award_id":"UL54 TR004130","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2887041666","display_name":"QuBBD: From Personalized Predictions to Better Control of Chronic Health Conditions","funder_award_id":"1664644","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3024551116","display_name":null,"funder_award_id":"N00014-19-1-2571","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3631731549","display_name":null,"funder_award_id":"N00014-17-1-2304","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4504108201","display_name":null,"funder_award_id":"N00014-17-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5972442391","display_name":null,"funder_award_id":"N00014-19","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6460852052","display_name":"SCH: INT: Distributed Analytics for Enhancing Fertility in Families","funder_award_id":"1914792","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8929337198","display_name":null,"funder_award_id":"N00014-17","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"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/W112666333","https://openalex.org/W1483373940","https://openalex.org/W1757796397","https://openalex.org/W1771410628","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/W2756826236","https://openalex.org/W2757631751","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2938321354","https://openalex.org/W2942608247","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/W4289258965","https://openalex.org/W6680724558"],"related_works":["https://openalex.org/W4226100475","https://openalex.org/W2977322142","https://openalex.org/W6903680946","https://openalex.org/W3012995883","https://openalex.org/W2908763886","https://openalex.org/W3081788171","https://openalex.org/W3143003892","https://openalex.org/W4327521011","https://openalex.org/W2347074400","https://openalex.org/W7097368714"],"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":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-09-16T00:00:00"}