{"id":"https://openalex.org/W3094113003","doi":"https://doi.org/10.1109/cog47356.2020.9231608","title":"Reinforcement Learning with Action-Specific Focuses in Video Games","display_name":"Reinforcement Learning with Action-Specific Focuses in Video Games","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3094113003","doi":"https://doi.org/10.1109/cog47356.2020.9231608","mag":"3094113003"},"language":"en","primary_location":{"id":"doi:10.1109/cog47356.2020.9231608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231608","pdf_url":null,"source":{"id":"https://openalex.org/S4306498668","display_name":"2020 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Conference on Games (CoG)","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/A5113820194","display_name":"Wang Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Meng","raw_affiliation_strings":["Fuxi AI Lab in Netease, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103121632","display_name":"Yingfeng Chen","orcid":"https://orcid.org/0000-0002-9747-5947"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yingfeng","raw_affiliation_strings":["Fuxi AI Lab in Netease, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042252596","display_name":"Tangjie Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lv Tangjie","raw_affiliation_strings":["Fuxi AI Lab in Netease, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381751","display_name":"Yan Song","orcid":"https://orcid.org/0000-0001-7050-4368"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Yan","raw_affiliation_strings":["Fuxi AI Lab in Netease, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006918020","display_name":"Kai Guan","orcid":"https://orcid.org/0000-0003-3582-3464"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guan Kai","raw_affiliation_strings":["Fuxi AI Lab in Netease, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022008180","display_name":"Changjie Fan","orcid":"https://orcid.org/0000-0001-5420-0516"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Changjie","raw_affiliation_strings":["Fuxi AI Lab in Netease, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Yang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"518","issue":null,"first_page":"9","last_page":"16"},"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":0.9891999959945679,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9873999953269958,"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":0.8685362935066223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774028778076172},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7396914958953857},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6350204348564148},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6209459900856018},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5992684960365295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765095949172974},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4792861342430115},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4721251428127289},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33569276332855225},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07195261120796204}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8685362935066223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774028778076172},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7396914958953857},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6350204348564148},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6209459900856018},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5992684960365295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765095949172974},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4792861342430115},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4721251428127289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33569276332855225},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07195261120796204},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog47356.2020.9231608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231608","pdf_url":null,"source":{"id":"https://openalex.org/S4306498668","display_name":"2020 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1581202840","https://openalex.org/W1999567494","https://openalex.org/W2133564696","https://openalex.org/W2145339207","https://openalex.org/W2162724220","https://openalex.org/W2195446438","https://openalex.org/W2257979135","https://openalex.org/W2333091651","https://openalex.org/W2418628973","https://openalex.org/W2530887700","https://openalex.org/W2736601468","https://openalex.org/W2771807014","https://openalex.org/W2776207810","https://openalex.org/W2786928559","https://openalex.org/W2807340089","https://openalex.org/W2899077443","https://openalex.org/W2942437031","https://openalex.org/W2950560044","https://openalex.org/W2960661612","https://openalex.org/W2962894046","https://openalex.org/W2963126744","https://openalex.org/W2963277051","https://openalex.org/W2963403868","https://openalex.org/W2963495494","https://openalex.org/W2963727600","https://openalex.org/W2964158321","https://openalex.org/W2964308564","https://openalex.org/W2968202530","https://openalex.org/W3004129452","https://openalex.org/W3037207827","https://openalex.org/W3037790619","https://openalex.org/W4288614963","https://openalex.org/W4299805595","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6679434410","https://openalex.org/W6684088912","https://openalex.org/W6687590523","https://openalex.org/W6717018068","https://openalex.org/W6718092244","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6746042458","https://openalex.org/W6748554570","https://openalex.org/W6752216966","https://openalex.org/W6752781648","https://openalex.org/W6755654293","https://openalex.org/W6759315145","https://openalex.org/W6780058518","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2028665553"],"abstract_inverted_index":{"It":[0],"is":[1,64,105,133],"intuitive":[2],"that":[3,118,131,152],"different":[4,7,50,54,85,107,160],"actions":[5],"prefer":[6],"information":[8,20],"in":[9,34,75,115,139],"human":[10,30],"decisions.":[11],"However,":[12],"classical":[13],"reinforcement":[14,116],"learning":[15,53,117],"models":[16],"use":[17],"the":[18,57,60,69,72,91,95,109,123,127,137,145,148],"same":[19],"process":[21,32],"procedure":[22],"for":[23,71,98],"all":[24],"actions.":[25,55,161],"In":[26,56],"order":[27],"to":[28,93,135],"imitate":[29],"decision-making":[31],"closer,":[33],"this":[35],"paper":[36],"we":[37],"investigate":[38],"a":[39],"new":[40],"policy":[41],"model,":[42],"i.e.,":[43],"Action-Specific":[44],"Focuses":[45],"(ASF)":[46],"framework,":[47,59],"which":[48,76],"enables":[49,90],"focuses":[51,157],"when":[52,158],"ASF":[58,103,132,153],"whole":[61],"action":[62,100],"set":[63],"taken":[65],"as":[66],"part":[67],"of":[68,112,142,147],"queries":[70],"attention":[73,113,149],"module,":[74],"state-dependent":[77],"action-specific":[78,86],"features":[79],"can":[80,154],"be":[81],"generated.":[82],"Through":[83],"extracting":[84],"features,":[87],"our":[88],"approach":[89],"agent":[92],"learn":[94,155],"action-focus":[96],"map":[97],"each":[99],"separately.":[101],"The":[102],"framework":[104],"also":[106],"from":[108],"previous":[110],"usages":[111],"mechanisms":[114],"are":[119],"mostly":[120],"based":[121],"on":[122,126],"state.":[124],"Experiments":[125],"Atari":[128],"benchmark":[129],"show":[130],"able":[134],"improve":[136],"performance":[138],"various":[140],"types":[141],"games.":[143],"Moreover,":[144],"visualizations":[146],"weights":[150],"suggest":[151],"meaningful":[156],"taking":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}