{"id":"https://openalex.org/W2092430508","doi":"https://doi.org/10.1109/cec.2014.6900246","title":"Learning a Super Mario controller from examples of human play","display_name":"Learning a Super Mario controller from examples of human play","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2092430508","doi":"https://doi.org/10.1109/cec.2014.6900246","mag":"2092430508"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2014.6900246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2014.6900246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Learning_a_super_mario_controller_from_examples_of_human_play/27390810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110144035","display_name":"Geoffrey Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Geoffrey Lee","raw_affiliation_strings":["School of Computer Science and Information Technology, RMIT University, Australia","School of Computer Science and Information Technology, RMIT Univ., Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University, Australia","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT Univ., Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088772141","display_name":"Min Luo","orcid":"https://orcid.org/0000-0002-2880-7186"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Min Luo","raw_affiliation_strings":["School of Computer Science and Information Technology, RMIT University, Australia","School of Computer Science and Information Technology, RMIT Univ., Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University, Australia","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT Univ., Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061528333","display_name":"Fabio Zambetta","orcid":"https://orcid.org/0000-0003-4133-7913"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fabio Zambetta","raw_affiliation_strings":["School of Computer Science and Information Technology, RMIT University, Australia","School of Computer Science and Information Technology, RMIT Univ., Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University, Australia","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT Univ., Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369719","display_name":"Xiaodong Li","orcid":"https://orcid.org/0000-0003-0346-1526"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaodong Li","raw_affiliation_strings":["School of Computer Science and Information Technology, RMIT University, Australia","School of Computer Science and Information Technology, RMIT Univ., Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT University, Australia","institution_ids":["https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology, RMIT Univ., Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":1.2417,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.81721108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9959999918937683,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7362278699874878},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6906735897064209},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6640926599502563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6591894030570984},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5923311114311218},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5827802419662476},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.500556230545044},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49720481038093567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3397887051105499},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3350526988506317},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.219623863697052},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13864129781723022},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11963707208633423},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08685824275016785},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07806679606437683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362278699874878},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6906735897064209},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6640926599502563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6591894030570984},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5923311114311218},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5827802419662476},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.500556230545044},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49720481038093567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3397887051105499},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3350526988506317},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.219623863697052},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13864129781723022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11963707208633423},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08685824275016785},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07806679606437683},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cec.2014.6900246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2014.6900246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.2032","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.2032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://goanna.cs.rmit.edu.au/~xiaodong/publications/min-mario-cec14.pdf","raw_type":"text"},{"id":"pmh:oai:alma61RMIT.INST:11247036360001341","is_oa":false,"landing_page_url":"http://doi.org/10.1109/CEC.2014.6900246","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27390810","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Learning_a_super_mario_controller_from_examples_of_human_play/27390810","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27390810","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Learning_a_super_mario_controller_from_examples_of_human_play/27390810","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W143632683","https://openalex.org/W167175497","https://openalex.org/W1497870361","https://openalex.org/W1507852408","https://openalex.org/W1591675293","https://openalex.org/W1982542138","https://openalex.org/W1999874108","https://openalex.org/W2010843562","https://openalex.org/W2050787672","https://openalex.org/W2070992004","https://openalex.org/W2085305319","https://openalex.org/W2109910161","https://openalex.org/W2113168737","https://openalex.org/W2115668428","https://openalex.org/W2116039916","https://openalex.org/W2117675763","https://openalex.org/W2121863487","https://openalex.org/W2131843096","https://openalex.org/W2136065562","https://openalex.org/W2137285991","https://openalex.org/W2162009473","https://openalex.org/W2166834249","https://openalex.org/W2166993268","https://openalex.org/W2171494278","https://openalex.org/W2191395120","https://openalex.org/W2737560561","https://openalex.org/W2949600864","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6606705844","https://openalex.org/W6629097285","https://openalex.org/W6635261211","https://openalex.org/W6677555207","https://openalex.org/W6683971778","https://openalex.org/W6684097133","https://openalex.org/W6684978684"],"related_works":["https://openalex.org/W4400868993","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"],"abstract_inverted_index":{"Imitating":[0],"human-like":[1,24,33],"behaviour":[2,34,87],"in":[3,12,101],"action":[4],"games":[5],"is":[6,115,124],"a":[7,43,118],"challenging":[8],"but":[9],"intriguing":[10],"task":[11,51],"Artificial":[13],"Intelligence":[14],"research,":[15],"with":[16],"various":[17],"strategies":[18],"being":[19,40],"employed":[20],"to":[21,48,70,97,149,158],"solve":[22],"the":[23,50,64,72,98,122,127,132,165],"imitation":[25],"problem.":[26],"In":[27],"this":[28,67],"research":[29],"we":[30,84,146],"consider":[31],"learning":[32,47,96,141],"via":[35,142],"Markov":[36],"decision":[37],"processes":[38],"without":[39],"explicitly":[41],"given":[42],"reward":[44,90],"function,":[45],"and":[46,66,89,121],"perform":[49],"by":[52,92,117,126,138],"observing":[53],"expert's":[54],"demonstration.":[55],"Individual":[56],"players":[57],"often":[58],"have":[59],"characteristic":[60],"styles":[61],"when":[62],"playing":[63,164],"game,":[65,166],"method":[68],"attempts":[69],"find":[71],"behaviours":[73],"which":[74,108,154],"make":[75],"them":[76],"unique.":[77],"During":[78],"play":[79],"sessions":[80],"of":[81,160],"Super":[82],"Mario":[83],"calculate":[85],"player's":[86,99,133],"policies":[88],"functions":[91],"applying":[93],"inverse":[94],"reinforcement":[95],"actions":[100],"game.":[102],"We":[103,135],"conduct":[104],"an":[105,151,161],"online":[106],"questionnaire":[107],"displays":[109],"two":[110],"video":[111],"clips,":[112],"where":[113],"one":[114],"played":[116,125],"human":[119,162],"expert":[120,163],"other":[123],"designed":[128],"controller":[129],"based":[130],"on":[131],"policy.":[134],"demonstrate":[136],"that":[137,159],"using":[139],"apprenticeship":[140],"Inverse":[143],"Reinforcement":[144],"Learning,":[145],"are":[147],"able":[148],"get":[150],"optimal":[152],"policy":[153],"yields":[155],"performance":[156],"close":[157],"at":[167],"least":[168],"under":[169],"specific":[170],"conditions.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}