{"id":"https://openalex.org/W3187758599","doi":"https://doi.org/10.1109/cec45853.2021.9505001","title":"Behavioral Cloning in Atari Games Using a Combined Variational Autoencoder and Predictor Model","display_name":"Behavioral Cloning in Atari Games Using a Combined Variational Autoencoder and Predictor Model","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3187758599","doi":"https://doi.org/10.1109/cec45853.2021.9505001","mag":"3187758599"},"language":"en","primary_location":{"id":"doi:10.1109/cec45853.2021.9505001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec45853.2021.9505001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101815006","display_name":"Brian Chen","orcid":"https://orcid.org/0000-0003-0757-0359"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Chen","raw_affiliation_strings":["University of Michigan,Department of Mathematics,Ann Arbor,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Mathematics,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071562605","display_name":"Siddhant Tandon","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Tandon","raw_affiliation_strings":["University of Michigan,Department of Aerospace Engineering,Ann Arbor,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Aerospace Engineering,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091098686","display_name":"David Gorsich","orcid":null},"institutions":[{"id":"https://openalex.org/I1304082316","display_name":"United States Department of the Army","ror":"https://ror.org/035w1gb98","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I4210088792","display_name":"United States Army","ror":"https://ror.org/00afsp483","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Gorsich","raw_affiliation_strings":["Ground Vehicle Systems Center U.S. Army DEVCOM,Warren,USA","Ground Vehicle Systems Center U.S. Army DEVCOM, Warren, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ground Vehicle Systems Center U.S. Army DEVCOM,Warren,USA","institution_ids":["https://openalex.org/I1304082316","https://openalex.org/I2802705668","https://openalex.org/I4210088792"]},{"raw_affiliation_string":"Ground Vehicle Systems Center U.S. Army DEVCOM, Warren, USA","institution_ids":["https://openalex.org/I1304082316","https://openalex.org/I2802705668","https://openalex.org/I4210088792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021570608","display_name":"Alex Gorodetsky","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Gorodetsky","raw_affiliation_strings":["University of Michigan,Department of Aerospace Engineering,Ann Arbor,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Aerospace Engineering,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004708744","display_name":"Shravan Veerapaneni","orcid":"https://orcid.org/0000-0002-2294-7233"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shravan Veerapaneni","raw_affiliation_strings":["University of Michigan,Department of Mathematics,Ann Arbor,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Mathematics,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61408451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2077","last_page":"2084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T11197","display_name":"Digital Games and Media","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.9636108875274658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950070261955261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6843767166137695},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.655689001083374},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5836284160614014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5564635992050171},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5511184334754944},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5510202646255493},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5225398540496826},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48342883586883545},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.44927796721458435},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.442740261554718},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3762495517730713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3432088792324066},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34010475873947144}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9636108875274658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950070261955261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6843767166137695},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.655689001083374},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5836284160614014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5564635992050171},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5511184334754944},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5510202646255493},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5225398540496826},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48342883586883545},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.44927796721458435},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.442740261554718},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3762495517730713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3432088792324066},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34010475873947144},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec45853.2021.9505001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec45853.2021.9505001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310328","display_name":"Automotive Research Center","ror":"https://ror.org/00jmfr291"},{"id":"https://openalex.org/F4320332447","display_name":"U.S. Army","ror":"https://ror.org/00afsp483"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W159980283","https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2061562262","https://openalex.org/W2145339207","https://openalex.org/W2604382266","https://openalex.org/W2619240030","https://openalex.org/W2735089625","https://openalex.org/W2962779270","https://openalex.org/W2963263347","https://openalex.org/W2963403143","https://openalex.org/W2964121744","https://openalex.org/W2964836580","https://openalex.org/W2997423597","https://openalex.org/W3008082783","https://openalex.org/W3034823751","https://openalex.org/W3035100622","https://openalex.org/W3041655446","https://openalex.org/W3094454393","https://openalex.org/W4297824719","https://openalex.org/W4391602018","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6726497184","https://openalex.org/W6737774802","https://openalex.org/W6741115023","https://openalex.org/W6773844738","https://openalex.org/W6780695443"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2988134182","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W1493875009","https://openalex.org/W4388844349","https://openalex.org/W2105231718","https://openalex.org/W2153939756"],"abstract_inverted_index":{"We":[0,10,79],"explore":[1],"an":[2,58],"approach":[3],"to":[4,13,75,84,101,124,136,143],"behavioral":[5],"cloning":[6,88],"in":[7,33],"video":[8],"games.":[9],"are":[11],"motivated":[12],"pursue":[14],"a":[15,42,50,65,69,90,104,108],"learning":[16],"architecture":[17,63],"that":[18,45,52],"is":[19],"data":[20],"efficient":[21],"and":[22,29,103,140],"provides":[23],"opportunity":[24],"for":[25,56],"interpreting":[26],"player":[27,31,138],"strategies":[28],"replicating":[30],"actions":[32,139],"unseen":[34],"situations.":[35],"To":[36],"this":[37],"end,":[38],"we":[39,113,116],"have":[40],"developed":[41],"generative":[43,122],"model":[44,82,92],"learns":[46],"latent":[47,73,130,145],"features":[48],"of":[49,121,132],"game":[51,98],"can":[53,117],"be":[54],"used":[55],"training":[57],"action":[59,76],"predictor.":[60],"Specifically,":[61],"our":[62,81],"combines":[64],"Variational":[66,105,134],"Autoencoder":[67,106,135],"with":[68,107],"discriminator":[70],"mapping":[71,97],"the":[72,119,129,133],"space":[74,131],"predictions":[77],"(predictor).":[78],"compare":[80],"performance":[83],"two":[85],"different":[86],"behavior":[87],"architectures:":[89],"discriminative":[91],"(a":[93],"Convolutional":[94],"Neural":[95],"Network)":[96],"states":[99,127],"directly":[100],"actions,":[102],"predictor":[109],"trained":[110],"separately.":[111],"Finally,":[112],"demonstrate":[114],"how":[115],"use":[118],"advantage":[120],"modeling":[123],"sample":[125],"new":[126],"from":[128],"analyze":[137],"provide":[141],"meaning":[142],"certain":[144],"features.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}