{"id":"https://openalex.org/W2897498038","doi":"https://doi.org/10.1109/cig.2018.8490423","title":"Learning Battles in ViZDoom via Deep Reinforcement Learning","display_name":"Learning Battles in ViZDoom via Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2897498038","doi":"https://doi.org/10.1109/cig.2018.8490423","mag":"2897498038"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2018.8490423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490423","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":"article","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/A5101787656","display_name":"Kun Shao","orcid":"https://orcid.org/0000-0003-0965-4302"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Shao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419530","display_name":"Nannan Li","orcid":"https://orcid.org/0000-0003-3688-6766"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101787656"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.5834,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94338992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9983999729156494,"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/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9079592227935791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7583131790161133},{"id":"https://openalex.org/keywords/battle","display_name":"Battle","score":0.7207043170928955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6895865797996521},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6318576335906982},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.562096893787384},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4683641195297241},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4636368155479431},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08613711595535278}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9079592227935791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583131790161133},{"id":"https://openalex.org/C2778627824","wikidata":"https://www.wikidata.org/wiki/Q178561","display_name":"Battle","level":2,"score":0.7207043170928955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6895865797996521},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6318576335906982},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.562096893787384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4683641195297241},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4636368155479431},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08613711595535278},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2018.8490423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2018.8490423","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2417089653","https://openalex.org/W2522489477","https://openalex.org/W2553701371","https://openalex.org/W2574978968","https://openalex.org/W2604279009","https://openalex.org/W2616729100","https://openalex.org/W2749807327","https://openalex.org/W2749928749","https://openalex.org/W2751516180","https://openalex.org/W2962747693","https://openalex.org/W2963871073","https://openalex.org/W2963890729","https://openalex.org/W2964043796","https://openalex.org/W4214717370","https://openalex.org/W4297804343","https://openalex.org/W6692846177","https://openalex.org/W6707268500","https://openalex.org/W6716653466","https://openalex.org/W6729788943","https://openalex.org/W6743660412","https://openalex.org/W6743756900"],"related_works":["https://openalex.org/W2003237632","https://openalex.org/W2120337598","https://openalex.org/W2350977361","https://openalex.org/W2348097125","https://openalex.org/W3030212771","https://openalex.org/W2000391299","https://openalex.org/W2994023542","https://openalex.org/W2999081595","https://openalex.org/W1558737772","https://openalex.org/W1968712166"],"abstract_inverted_index":{"First-person":[0],"shooter":[1],"(FPS)":[2],"video":[3],"games":[4],"play":[5],"an":[6,19],"important":[7],"role":[8],"in":[9,29,53,78,91],"game":[10],"artificial":[11],"intelligence":[12],"(AI).":[13],"In":[14,81],"this":[15],"paper,":[16],"we":[17],"present":[18],"effective":[20],"deep":[21],"reinforcement":[22],"learning":[23],"(DRL)":[24],"method":[25],"to":[26,76],"learn":[27],"battles":[28],"ViZDoom.":[30],"Our":[31],"approach":[32],"utilizes":[33],"the":[34,60,83,88,95],"actor-critic":[35,62],"with":[36,59],"Kronecker-factored":[37],"trust":[38],"region":[39],"(ACKTR),":[40],"a":[41,98],"sample-efficient":[42],"and":[43,57],"computationally":[44],"inexpensive":[45],"DRL":[46,71],"method.":[47],"We":[48],"train":[49],"our":[50],"ACKTR":[51,84],"agents":[52,75,85,90],"two":[54],"battle":[55,77],"scenarios,":[56],"compare":[58],"advantage":[61],"(A2C)":[63],"baseline":[64],"agent.":[65],"The":[66],"experimental":[67],"results":[68],"demonstrate":[69],"that":[70],"methods":[72],"successfully":[73],"teach":[74],"these":[79],"scenarios.":[80],"addition,":[82],"significantly":[86],"outperform":[87],"A2C":[89],"terms":[92],"of":[93],"all":[94],"metrics":[96],"by":[97],"significant":[99],"margin.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}