{"id":"https://openalex.org/W2790850591","doi":"https://doi.org/10.1109/cig.2018.8490398","title":"Imitation Learning with Concurrent Actions in 3D Games","display_name":"Imitation Learning with Concurrent Actions in 3D Games","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2790850591","doi":"https://doi.org/10.1109/cig.2018.8490398","mag":"2790850591"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2018.8490398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.05402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087941613","display_name":"Jack Harmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jack Harmer","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088043381","display_name":"Linus Gissl\u00e9n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linus Gisslen","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jorge del Val","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge del Val","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036769787","display_name":"Henrik Holst","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henrik Holst","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028726425","display_name":"Joakim Bergdahl","orcid":"https://orcid.org/0000-0001-5720-2533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joakim Bergdahl","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079968601","display_name":"Tom Olsson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Olsson","raw_affiliation_strings":["Electronic Arts, DICE, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, DICE, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031140763","display_name":"Kristoffer Sj\u00f6\u00f6","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristoffer Sjoo","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038782862","display_name":"Magnus Nordin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Magnus Nordin","raw_affiliation_strings":["Electronic Arts, SEED, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Arts, SEED, Stockholm, Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5087941613"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6775,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7667217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9962999820709229,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9925000071525574,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8713703751564026},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.7962594032287598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527234554290771},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6817379593849182},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.671840488910675},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6374613046646118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6314269304275513},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.49642258882522583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47762531042099},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4675081670284271},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09934848546981812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8713703751564026},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.7962594032287598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527234554290771},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6817379593849182},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.671840488910675},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6374613046646118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6314269304275513},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.49642258882522583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47762531042099},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4675081670284271},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09934848546981812},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cig.2018.8490398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.05402","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.05402","pdf_url":"https://arxiv.org/pdf/1803.05402","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2790850591","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1803.05402","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1803.05402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.05402","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.05402","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.05402","pdf_url":"https://arxiv.org/pdf/1803.05402","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2790850591.pdf","grobid_xml":"https://content.openalex.org/works/W2790850591.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1777239053","https://openalex.org/W1931877416","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2148112459","https://openalex.org/W2155968351","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2415726935","https://openalex.org/W2539164647","https://openalex.org/W2555255624","https://openalex.org/W2607198029","https://openalex.org/W2617816519","https://openalex.org/W2724169821","https://openalex.org/W2756826236","https://openalex.org/W2785379783","https://openalex.org/W2786800733","https://openalex.org/W2788862220","https://openalex.org/W2952523895","https://openalex.org/W2963423916","https://openalex.org/W2964043796","https://openalex.org/W6627932998","https://openalex.org/W6638088447","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6716193690","https://openalex.org/W6736609842","https://openalex.org/W6737984913","https://openalex.org/W6740092555","https://openalex.org/W6744564315","https://openalex.org/W6748221089","https://openalex.org/W6748314335","https://openalex.org/W6748395181","https://openalex.org/W6748645729","https://openalex.org/W6748972340"],"related_works":["https://openalex.org/W2050024476","https://openalex.org/W2994972935","https://openalex.org/W2786663522","https://openalex.org/W3124540781","https://openalex.org/W3123614573","https://openalex.org/W2958051327","https://openalex.org/W3131824536","https://openalex.org/W2195382509","https://openalex.org/W2294422333","https://openalex.org/W3127446034","https://openalex.org/W2986185262","https://openalex.org/W3167527548","https://openalex.org/W2912947802","https://openalex.org/W3041557432","https://openalex.org/W3183421534","https://openalex.org/W2786080048","https://openalex.org/W3036054814","https://openalex.org/W2934105217","https://openalex.org/W2982852993","https://openalex.org/W2528846071"],"abstract_inverted_index":{"In":[0],"this":[1,82],"work":[2],"we":[3],"describe":[4],"a":[5,60,85],"novel":[6],"deep":[7],"reinforcement":[8,55],"learning":[9,50,56,123],"architecture":[10],"that":[11,33],"allows":[12,103],"multiple":[13],"actions":[14],"to":[15,30,38,58,108,129],"be":[16,31,36,109],"selected":[17],"at":[18],"every":[19],"time-step":[20],"in":[21,63,69],"an":[22],"efficient":[23],"manner.":[24],"Multi-action":[25],"policies":[26],"allow":[27],"complex":[28,86],"behaviours":[29],"learnt":[32],"would":[34],"otherwise":[35],"hard":[37],"achieve":[39],"when":[40],"using":[41,84],"single":[42,72],"action":[43,73],"selection":[44,74],"techniques.":[45],"We":[46,77],"use":[47],"both":[48],"imitation":[49],"and":[51,66,102,124],"temporal":[52],"difference":[53],"(TD)":[54],"(RL)":[57],"provide":[59],"4x":[61],"improvement":[62,68],"training":[64,119],"time":[65],"2.5x":[67],"performance":[70],"over":[71],"TD":[75,114,122],"RL.":[76],"demonstrate":[78],"the":[79,91,94,104,125,131,134],"capabilities":[80,132],"of":[81,93,133],"network":[83],"in-house":[87],"3D":[88],"game.":[89],"Mimicking":[90],"behavior":[92],"expert":[95],"teacher":[96],"significantly":[97],"improves":[98],"world":[99],"state":[100],"exploration":[101],"agents":[105],"vision":[106],"system":[107],"trained":[110],"more":[111],"rapidly":[112],"than":[113],"RL":[115],"alone.":[116],"This":[117],"initial":[118],"technique":[120],"kick-starts":[121],"agent":[126],"quickly":[127],"learns":[128],"surpass":[130],"expert.":[135]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}