{"id":"https://openalex.org/W3126698741","doi":"https://doi.org/10.1109/bibm49941.2020.9313387","title":"Large Scale Deep Reinforcement Learning in War-games","display_name":"Large Scale Deep Reinforcement Learning in War-games","publication_year":2020,"publication_date":"2020-12-16","ids":{"openalex":"https://openalex.org/W3126698741","doi":"https://doi.org/10.1109/bibm49941.2020.9313387","mag":"3126698741"},"language":"en","primary_location":{"id":"doi:10.1109/bibm49941.2020.9313387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5102718627","display_name":"Hanchao Wang","orcid":"https://orcid.org/0000-0002-9719-4790"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanchao Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176048","display_name":"Hongyao Tang","orcid":"https://orcid.org/0000-0001-7478-7684"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyao Tang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137659","display_name":"Xiaotian Hao","orcid":"https://orcid.org/0000-0002-3084-8366"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotian Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010029387","display_name":"Yue Fu","orcid":"https://orcid.org/0000-0003-1076-1615"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Fu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101601194","display_name":"Yi Ma","orcid":"https://orcid.org/0000-0003-1832-8920"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ma","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1693","last_page":"1699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973999857902527,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.95660001039505,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8396041393280029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7559826374053955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914211273193359},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5458838939666748},{"id":"https://openalex.org/keywords/battlefield","display_name":"Battlefield","score":0.5096423625946045},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4454864263534546},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41088926792144775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3720630407333374},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.33476847410202026},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10033288598060608},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.08196523785591125}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8396041393280029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559826374053955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914211273193359},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5458838939666748},{"id":"https://openalex.org/C2779669469","wikidata":"https://www.wikidata.org/wiki/Q4895508","display_name":"Battlefield","level":2,"score":0.5096423625946045},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4454864263534546},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41088926792144775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3720630407333374},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.33476847410202026},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10033288598060608},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.08196523785591125},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C195244886","wikidata":"https://www.wikidata.org/wiki/Q41493","display_name":"Ancient history","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm49941.2020.9313387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1488730473","https://openalex.org/W1568042657","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2584377191","https://openalex.org/W2594829461","https://openalex.org/W2742132707","https://openalex.org/W2766447205","https://openalex.org/W2964161785","https://openalex.org/W2965676832","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3093287223"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W4319083788","https://openalex.org/W2376680721","https://openalex.org/W2127284606","https://openalex.org/W3032003174"],"abstract_inverted_index":{"War-game":[0],"is":[1,76,116,135],"a":[2,32,66,85,94,170],"type":[3],"of":[4,11,56,166],"multi-agent":[5,96],"real-time":[6],"strategy":[7],"game,":[8],"with":[9,159,204],"challenges":[10,206],"the":[12,17,26,59,70,107,123,151,155,164,167,183,205,208],"large-scale":[13],"decision-making":[14],"space":[15],"and":[16,19,39,46,141,153],"flexible":[18],"changeable":[20],"battlefield":[21],"situation.":[22],"In":[23,42,78,174],"addition":[24],"to":[25,52,83,100,188],"military":[27],"field,":[28],"it":[29,121,142],"has":[30],"played":[31],"role":[33],"in":[34,112,207],"fields":[35],"including":[36],"epidemic":[37],"prevention":[38],"pest":[40],"control.":[41],"recent":[43],"years,":[44],"more":[45,47],"learning":[48,98],"algorithms":[49],"have":[50,62],"tried":[51],"solve":[53,84],"this":[54,79],"kind":[55],"game.":[57],"However,":[58],"existing":[60],"methods":[61,200],"not":[63],"yet":[64],"given":[65],"satisfactory":[67],"solution":[68],"for":[69,106,118,138,149],"war-game,":[71],"especially":[72],"when":[73],"preparation":[74],"time":[75],"limited.":[77],"background,":[80],"we":[81,162,176],"try":[82],"traditional":[86],"war-game":[87],"based":[88],"on":[89],"hexagon":[90],"grids.":[91],"We":[92],"propose":[93],"hierarchical":[95,114,184],"reinforcement":[97],"framework":[99,115],"rapidly":[101],"training":[102],"an":[103],"AI":[104,195],"model":[105,168,196],"war-game.":[108,209],"The":[109,132],"higher-level":[110],"network":[111,134],"our":[113,199],"used":[117,137],"task":[119],"decision,":[120],"solves":[122],"credit":[124],"assignment":[125],"problem":[126],"between":[127],"agents":[128,152,187],"through":[129,146,169],"cooperative":[130],"training.":[131],"lower-level":[133],"mainly":[136],"route":[139],"planning,":[140],"can":[143,201],"be":[144],"reused":[145],"parameter":[147],"sharing":[148],"all":[150,154],"maps.":[156],"To":[157],"deal":[158,203],"various":[160],"opponents,":[161],"improve":[163],"robustness":[165],"grouped":[171],"self-play":[172],"approach.":[173],"experiments,":[175],"get":[177],"encouraging":[178],"results":[179],"which":[180],"show":[181],"that":[182,198],"structure":[185],"allows":[186],"learn":[189],"their":[190],"strategies":[191],"effectively.":[192],"Our":[193],"final":[194],"demonstrates":[197],"effectively":[202]},"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":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}