{"id":"https://openalex.org/W3081243957","doi":"https://doi.org/10.1145/3409501.3409517","title":"Value Function Dynamic Estimation in Reinforcement Learning based on Data Adequacy","display_name":"Value Function Dynamic Estimation in Reinforcement Learning based on Data Adequacy","publication_year":2020,"publication_date":"2020-07-03","ids":{"openalex":"https://openalex.org/W3081243957","doi":"https://doi.org/10.1145/3409501.3409517","mag":"3081243957"},"language":"en","primary_location":{"id":"doi:10.1145/3409501.3409517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409501.3409517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial Intelligence","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/A5090120348","display_name":"Huifan Gao","orcid":"https://orcid.org/0000-0002-8624-1301"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifan Gao","raw_affiliation_strings":["Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085263461","display_name":"Yinghui Pan","orcid":"https://orcid.org/0000-0001-5715-2855"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghui Pan","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077270486","display_name":"Jing Tang","orcid":"https://orcid.org/0000-0002-0785-707X"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jing Tang","raw_affiliation_strings":["Newcastle Business School, Northumbria University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle Business School, Northumbria University, UK","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653058","display_name":"Yifeng Zeng","orcid":"https://orcid.org/0000-0002-5246-403X"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yifeng Zeng","raw_affiliation_strings":["Department of Computer & Information Sciences, Northumbria University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer & Information Sciences, Northumbria University, UK","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007631602","display_name":"Peihua Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihua Chai","raw_affiliation_strings":["Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101936719","display_name":"Langcai Cao","orcid":"https://orcid.org/0000-0001-6388-1413"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Langcai Cao","raw_affiliation_strings":["Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision, Department of Automation, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4062,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69822117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"208"},"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":0.9879000186920166,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9710999727249146,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8149948120117188},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7872612476348877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7378669381141663},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6366379261016846},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6306962370872498},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5615414381027222},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4556562900543213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4139326214790344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33537042140960693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15007027983665466},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08197575807571411}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8149948120117188},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7872612476348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378669381141663},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6366379261016846},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6306962370872498},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5615414381027222},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4556562900543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4139326214790344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33537042140960693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15007027983665466},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08197575807571411},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3409501.3409517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409501.3409517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1534413527","https://openalex.org/W1980772289","https://openalex.org/W2080834410","https://openalex.org/W2145495721","https://openalex.org/W2257979135","https://openalex.org/W2766447205","https://openalex.org/W2791207714","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"In":[0,49],"recent":[1],"years,":[2],"reinforcement":[3],"learning":[4],"has":[5],"played":[6],"an":[7],"important":[8],"role":[9],"in":[10,16,58,80,95],"the":[11,21,28,52,59,74,85,89,99,103,110,113],"study":[12],"of":[13,23,42,51,55,88,112],"decision":[14],"problem":[15,22],"computer":[17],"games.":[18],"To":[19],"solve":[20],"how":[24],"to":[25],"better":[26,117],"estimate":[27],"value":[29,43,66,76],"function":[30,44,67,77],"with":[31,102],"limited":[32],"computational":[33],"resources,":[34],"this":[35],"paper":[36],"proposes":[37],"a":[38,64],"dynamic":[39,65],"estimation":[40,68,78],"method":[41,69,79,101],"based":[45],"on":[46,84],"data":[47],"adequacy.":[48],"consideration":[50],"varying":[53],"complexity":[54],"each":[56],"state":[57],"MDP":[60],"model,":[61],"we":[62,97],"propose":[63],"which":[70],"is":[71,116],"different":[72],"from":[73],"fixed":[75],"traditional":[81,119],"methods.":[82],"Based":[83],"PigChase":[86],"challenge":[87],"Malmo":[90],"project":[91],"launched":[92],"by":[93],"Microsoft":[94],"2017,":[96],"compare":[98],"new":[100],"existing":[104],"techniques.":[105],"Experimental":[106],"results":[107],"show":[108],"that":[109],"performance":[111],"proposed":[114],"algorithm":[115],"than":[118],"algorithms.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}