{"id":"https://openalex.org/W3206820790","doi":"https://doi.org/10.1007/s10462-021-10085-1","title":"Model-free reinforcement learning from expert demonstrations: a survey","display_name":"Model-free reinforcement learning from expert demonstrations: a survey","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W3206820790","doi":"https://doi.org/10.1007/s10462-021-10085-1","mag":"3206820790"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-021-10085-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10462-021-10085-1","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.lib.cranfield.ac.uk/handle/1826/17203","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100688217","display_name":"Jorge Ram\u00edrez","orcid":"https://orcid.org/0000-0002-9606-2526"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Jorge Ram\u00edrez","raw_affiliation_strings":["Departamento de Control Autom\u00e1tico, CINVESTAV-IPN (National Polytechnic Institute), Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN (National Polytechnic Institute), Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008201587","display_name":"Wen Yu","orcid":"https://orcid.org/0000-0002-9540-7924"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Wen Yu","raw_affiliation_strings":["Departamento de Control Autom\u00e1tico, CINVESTAV-IPN (National Polytechnic Institute), Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN (National Polytechnic Institute), Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065156490","display_name":"Adolfo Perrusqu\u00eda","orcid":"https://orcid.org/0000-0003-2290-1160"},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adolfo Perrusqu\u00eda","raw_affiliation_strings":["School of Aerospace, Transport and Manufacturing, Cranfield University, Bedford, UK"],"affiliations":[{"raw_affiliation_string":"School of Aerospace, Transport and Manufacturing, Cranfield University, Bedford, UK","institution_ids":["https://openalex.org/I82284825"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100688217"],"corresponding_institution_ids":["https://openalex.org/I68368234"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":null,"fwci":9.9391,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.98481268,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"55","issue":"4","first_page":"3213","last_page":"3241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980000257492065,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8386529088020325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683203816413879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5166388154029846},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5083767771720886},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4960051476955414},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.486694872379303},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.45978453755378723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39470598101615906},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36087673902511597},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08702266216278076}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8386529088020325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683203816413879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5166388154029846},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5083767771720886},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4960051476955414},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.486694872379303},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.45978453755378723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39470598101615906},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36087673902511597},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08702266216278076},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10462-021-10085-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10462-021-10085-1","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},{"id":"pmh:oai:dspace.lib.cranfield.ac.uk:1826/17203","is_oa":true,"landing_page_url":"https://dspace.lib.cranfield.ac.uk/handle/1826/17203","pdf_url":null,"source":{"id":"https://openalex.org/S4306401778","display_name":"CERES (Cranfield University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82284825","host_organization_name":"Cranfield University","host_organization_lineage":["https://openalex.org/I82284825"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.cranfield.ac.uk:1826/17203","is_oa":true,"landing_page_url":"https://dspace.lib.cranfield.ac.uk/handle/1826/17203","pdf_url":null,"source":{"id":"https://openalex.org/S4306401778","display_name":"CERES (Cranfield University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82284825","host_organization_name":"Cranfield University","host_organization_lineage":["https://openalex.org/I82284825"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W100327610","https://openalex.org/W192920577","https://openalex.org/W356219054","https://openalex.org/W1515851193","https://openalex.org/W1516835682","https://openalex.org/W1557517019","https://openalex.org/W1601081659","https://openalex.org/W1845972764","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W1990005421","https://openalex.org/W2031580264","https://openalex.org/W2056653303","https://openalex.org/W2117864026","https://openalex.org/W2121863487","https://openalex.org/W2124267516","https://openalex.org/W2130801532","https://openalex.org/W2131825035","https://openalex.org/W2137375617","https://openalex.org/W2145339207","https://openalex.org/W2152161277","https://openalex.org/W2155968351","https://openalex.org/W2159566498","https://openalex.org/W2163922914","https://openalex.org/W2164114810","https://openalex.org/W2165150801","https://openalex.org/W2173564293","https://openalex.org/W2253157232","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2280163991","https://openalex.org/W2291973609","https://openalex.org/W2294089271","https://openalex.org/W2341171179","https://openalex.org/W2397581010","https://openalex.org/W2397607997","https://openalex.org/W2415726935","https://openalex.org/W2480004914","https://openalex.org/W2487144912","https://openalex.org/W2491675558","https://openalex.org/W2594103415","https://openalex.org/W2740302738","https://openalex.org/W2741122588","https://openalex.org/W2745868649","https://openalex.org/W2746553466","https://openalex.org/W2788862220","https://openalex.org/W2837981523","https://openalex.org/W2886265050","https://openalex.org/W2904157920","https://openalex.org/W2933058008","https://openalex.org/W2942910319","https://openalex.org/W2946416741","https://openalex.org/W2958051327","https://openalex.org/W2963024489","https://openalex.org/W2963099939","https://openalex.org/W2963313316","https://openalex.org/W2963411833","https://openalex.org/W2963477884","https://openalex.org/W2963754245","https://openalex.org/W2964227158","https://openalex.org/W2964407556","https://openalex.org/W2964836580","https://openalex.org/W2965723696","https://openalex.org/W2974295111","https://openalex.org/W2982316857","https://openalex.org/W2982852993","https://openalex.org/W2994446013","https://openalex.org/W2997874851","https://openalex.org/W2998396902","https://openalex.org/W3003852841","https://openalex.org/W3006001650","https://openalex.org/W3011942379","https://openalex.org/W3016327299","https://openalex.org/W3017000215","https://openalex.org/W3018036994","https://openalex.org/W3022566517","https://openalex.org/W3029539653","https://openalex.org/W3035597485","https://openalex.org/W3037625705","https://openalex.org/W3100789280","https://openalex.org/W3122106879","https://openalex.org/W3129322645","https://openalex.org/W3139377883","https://openalex.org/W4252387763","https://openalex.org/W4285719527","https://openalex.org/W6600062020","https://openalex.org/W6600210674","https://openalex.org/W6603732165","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2920061524"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":15}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}