{"id":"https://openalex.org/W2994530990","doi":null,"title":"Deep Reinforcement Learning with VizDoom First-Person Shooter","display_name":"Deep Reinforcement Learning with VizDoom First-Person Shooter","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2994530990","mag":"2994530990"},"language":"en","primary_location":{"id":"pmh:oai::97307","doi":null,"is_oa":false,"landing_page_url":"https://mpra.ub.uni-muenchen.de/97307/1/paper1.pdf","pdf_url":"https://mpra.ub.uni-muenchen.de/97307/1/paper1.pdf","source":{"id":"https://openalex.org/S4306400553","display_name":"Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"MPRA Paper"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"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/A5088008896","display_name":"Dmitry Aleksandrovich Akimov","orcid":"https://orcid.org/0000-0001-6889-618X","observed_orcids":["https://orcid.org/0000-0001-6889-618X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitry Akimov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074238659","display_name":"Ilya Makarov","orcid":"https://orcid.org/0000-0002-3308-8825","observed_orcids":["https://orcid.org/0000-0002-3308-8825"]},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ilya Makarov","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3308-8825","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0008999999845400453,"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/T13904","display_name":"Artificial Intelligence Applications","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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9929999709129333},{"id":"https://openalex.org/keywords/vizdoom","display_name":"ViZDoom","score":0.8970000147819519},{"id":"https://openalex.org/keywords/first-person-shooter-games","display_name":"first-person shooter games","score":0.9049999713897705},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.7580000162124634},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.859000027179718},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.734000027179718},{"id":"https://openalex.org/keywords/prioritized-experience-replay","display_name":"prioritized experience replay","score":0.9700000286102295},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.882041871547699},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8611329793930054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401461005210876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6112344264984131},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5793815851211548},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5695381760597229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37336966395378113},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29162803292274475},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.24739068746566772},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2464938461780548},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai::97307","doi":null,"is_oa":false,"landing_page_url":"https://mpra.ub.uni-muenchen.de/97307/1/paper1.pdf","pdf_url":"https://mpra.ub.uni-muenchen.de/97307/1/paper1.pdf","source":{"id":"https://openalex.org/S4306400553","display_name":"Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"MPRA Paper"},{"id":"pmh:oai:RePEc:pra:mprapa:97307","doi":null,"is_oa":false,"landing_page_url":"https://mpra.ub.uni-muenchen.de/97307/1/paper1.pdf","pdf_url":"https://mpra.ub.uni-muenchen.de/97307/1/paper1.pdf","source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"preprint"},{"id":"mag:2994530990","doi":null,"is_oa":false,"landing_page_url":"https://econpapers.repec.org/RePEc:pra:mprapa:97307","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"RePEc: Research Papers in Economics","raw_type":null},{"id":"mag:3168049713","doi":null,"is_oa":false,"landing_page_url":"https://ideas.repec.org/p/pra/mprapa/97307.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400553","display_name":"Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MPRA Paper","raw_type":null},{"id":"mag:3001427399","doi":null,"is_oa":false,"landing_page_url":"https://publications.hse.ru/chapters/318645398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3196238285","https://openalex.org/W4391164281","https://openalex.org/W4415756119","https://openalex.org/W3203385303","https://openalex.org/W2776133043","https://openalex.org/W2963860084","https://openalex.org/W4408249630","https://openalex.org/W2810526232","https://openalex.org/W2964822444","https://openalex.org/W4394643235"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,20],"study":[4],"deep":[5,49],"reinforcement":[6,50],"algorithms":[7],"forpartially":[8],"observable":[9],"Markov":[10],"decision":[11,27],"processes":[12],"(POMDP)":[13],"combined":[14],"withDeep":[15],"Q-Networks.":[16],"To":[17],"our":[18,81],"knowledge,":[19],"are":[21],"the":[22,66],"first":[23],"to":[24,30,45,104],"apply":[25],"standardMarkov":[26],"process":[28],"architectures":[29],"POMDP":[31,107],"scenarios.":[32],"We":[33,61,79],"proposean":[34],"extension":[35],"of":[36,57],"DQN":[37,85],"with":[38,83,86],"Dueling":[39],"Networks":[40],"and":[41,93,113],"several":[42,63],"other":[43],"model-freepolicies":[44],"training":[46],"agent":[47,82,92,124],"using":[48],"learning":[51],"in":[52,69],"VizDoomenvironment,":[53],"which":[54],"is":[55,102],"replication":[56],"Doom":[58],"first-person":[59],"shooter.":[60],"de-velop":[62],"agents":[64],"for":[65,121],"following":[67],"scenarios":[68,116],"VizDoom":[70],"first-personshooter":[71],"(FPS):":[72],"Basic,":[73],"Defend":[74],"The":[75],"Center,":[76],"Health":[77],"Gathering.":[78],"com-pare":[80],"Recurrent":[84],"Prioritized":[87],"Experience":[88],"Replayand":[89],"Snapshot":[90],"Ensembling":[91],"get":[94],"approximately":[95],"triple":[96],"increase":[97],"inper":[98],"episode":[99],"reward.":[100],"It":[101],"important":[103],"say":[105],"that":[106],"scenario":[108],"closethe":[109],"gap":[110],"between":[111],"human":[112],"computer":[114],"player":[115],"thus":[117],"providingmore":[118],"meaningful":[119],"justification":[120],"Deep":[122],"RL":[123],"performance.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2019-12-13T00:00:00"}