{"id":"https://openalex.org/W3094490555","doi":"https://doi.org/10.1109/cog47356.2020.9231562","title":"Exploring Unknown States with Action Balance","display_name":"Exploring Unknown States with Action Balance","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3094490555","doi":"https://doi.org/10.1109/cog47356.2020.9231562","mag":"3094490555"},"language":"en","primary_location":{"id":"doi:10.1109/cog47356.2020.9231562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231562","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":null,"display_name":"Song Yan","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":"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/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/A5104264364","display_name":"Yujing Hu","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":"Hu Yujing","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/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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"191"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9962999820709229,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.8063737154006958},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7426475882530212},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7350763082504272},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.7101707458496094},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.6926155686378479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6387765407562256},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5725528597831726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5313730239868164},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45253098011016846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33248668909072876},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.32206106185913086},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1775990128517151},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1688920259475708},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15611004829406738},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09660649299621582},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09190356731414795},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07575774192810059}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8063737154006958},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7426475882530212},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7350763082504272},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.7101707458496094},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.6926155686378479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387765407562256},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5725528597831726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313730239868164},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45253098011016846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33248668909072876},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.32206106185913086},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1775990128517151},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1688920259475708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15611004829406738},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09660649299621582},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09190356731414795},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07575774192810059},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog47356.2020.9231562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231562","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1625390266","https://openalex.org/W1777239053","https://openalex.org/W2012833704","https://openalex.org/W2082691056","https://openalex.org/W2145339207","https://openalex.org/W2161966552","https://openalex.org/W2168405694","https://openalex.org/W2423557781","https://openalex.org/W2489939061","https://openalex.org/W2561776174","https://openalex.org/W2596982695","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2766447205","https://openalex.org/W2895453875","https://openalex.org/W2902298341","https://openalex.org/W2914261249","https://openalex.org/W2949475445","https://openalex.org/W2963049774","https://openalex.org/W2963160877","https://openalex.org/W2963276097","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2963636093","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2964185768","https://openalex.org/W2965050397","https://openalex.org/W2965435131","https://openalex.org/W2969456553","https://openalex.org/W2996695841","https://openalex.org/W4230940751","https://openalex.org/W4287867830","https://openalex.org/W4288266427","https://openalex.org/W6636578284","https://openalex.org/W6638088447","https://openalex.org/W6683603353","https://openalex.org/W6692846177","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6741002519","https://openalex.org/W6752725515","https://openalex.org/W6754957883","https://openalex.org/W6756303580","https://openalex.org/W6757058172","https://openalex.org/W6758978475","https://openalex.org/W6766694020","https://openalex.org/W6771807793"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2386723501","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W3011883280","https://openalex.org/W2497074849"],"abstract_inverted_index":{"Exploration":[0],"is":[1,19,43,90],"a":[2,136,198],"key":[3],"problem":[4],"in":[5,15,78,106,201,212],"reinforcement":[6,153],"learning.":[7,154],"Recently":[8],"bonus-based":[9],"methods":[10,60,70,166],"have":[11],"achieved":[12],"considerable":[13],"successes":[14],"environments":[16,216],"where":[17],"exploration":[18,89,177,196,215],"difficult":[20],"such":[21,59],"as":[22,61,143],"Montezuma's":[23],"Revenge,":[24],"which":[25,98,127],"assign":[26],"additional":[27],"bonuses":[28],"(e.g.,":[29,167],"intrinsic":[30],"rewards)":[31],"to":[32,36,46,74,151,178],"guide":[33],"the":[34,41,47,50,62,67,72,88,93,101,116,129,163,187,208],"agent":[35,73],"rarely":[37],"visited":[38],"states.":[39],"Since":[40],"bonus":[42,64,69,165],"calculated":[44],"according":[45],"novelty":[48],"of":[49,103,118,131,146,181,210],"next":[51,94],"state":[52,95,138],"after":[53],"performing":[54],"an":[55,144],"action,":[56],"we":[57,112,156],"call":[58],"next-state":[63,68,164],"methods.":[65],"However,":[66],"force":[71],"pay":[75],"overmuch":[76],"attention":[77],"exploring":[79],"known":[80],"states":[81,86,121,204],"and":[82,122,139,173,190,205],"ignore":[83],"finding":[84,104,119,202],"unknown":[85,120,203],"since":[87],"driven":[91],"by":[92],"already":[96],"visited,":[97],"may":[99],"slow":[100],"pace":[102],"reward":[105],"some":[107,213],"environments.":[108],"In":[109],"this":[110],"paper,":[111],"focus":[113],"on":[114,186],"improving":[115],"effectiveness":[117],"propose":[123,157],"action":[124,134,158,175,194],"balance":[125,159,176,195],"exploration,":[126,171],"balances":[128],"frequency":[130],"selecting":[132],"each":[133],"at":[135],"given":[137],"can":[140,206],"be":[141],"treated":[142],"extension":[145],"upper":[147],"confidence":[148],"bound":[149],"(UCB)":[150],"deep":[152],"Moreover,":[155],"RND":[160,211],"that":[161],"combines":[162],"random":[168],"network":[169],"distillation":[170],"RND)":[172],"our":[174],"take":[179],"advantage":[180],"both":[182],"sides.":[183],"The":[184],"experiments":[185],"grid":[188],"world":[189],"Atari":[191],"games":[192],"demonstrate":[193],"has":[197],"better":[199],"capability":[200],"improve":[207],"performance":[209],"hard":[214],"respectively.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}