{"id":"https://openalex.org/W3009423269","doi":"https://doi.org/10.1145/3374587.3374595","title":"Reinforcement Learning Based on Multi-subnet Clusters","display_name":"Reinforcement Learning Based on Multi-subnet Clusters","publication_year":2019,"publication_date":"2019-12-06","ids":{"openalex":"https://openalex.org/W3009423269","doi":"https://doi.org/10.1145/3374587.3374595","mag":"3009423269"},"language":"en","primary_location":{"id":"doi:10.1145/3374587.3374595","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374587.3374595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Computer Science 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/A5100625049","display_name":"Xiaobing Wang","orcid":"https://orcid.org/0000-0001-5044-3721"},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaobing Wang","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049384079","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0001-7908-4881"},"institutions":[{"id":"https://openalex.org/I74525822","display_name":"Hubei University of Technology","ror":"https://ror.org/02d3fj342","country_code":"CN","type":"education","lineage":["https://openalex.org/I74525822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["School of Computer Science, Hubei University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I74525822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100625049"],"corresponding_institution_ids":["https://openalex.org/I74525822"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20081472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9603000283241272,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9455000162124634,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/subnet","display_name":"Subnet","score":0.9449695348739624},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.82887864112854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6977577209472656},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6216660737991333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35871627926826477},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14988973736763},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14393708109855652}],"concepts":[{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.9449695348739624},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.82887864112854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6977577209472656},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6216660737991333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35871627926826477},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14988973736763},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14393708109855652},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3374587.3374595","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374587.3374595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1543614656","https://openalex.org/W1598866093","https://openalex.org/W2048226872","https://openalex.org/W2138309709","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2177410802","https://openalex.org/W2601298905","https://openalex.org/W2724169821","https://openalex.org/W2739473244","https://openalex.org/W2761873684","https://openalex.org/W2786928559","https://openalex.org/W2963423916","https://openalex.org/W2964043796","https://openalex.org/W4214717370","https://openalex.org/W4246464108","https://openalex.org/W4285719527","https://openalex.org/W6687681856"],"related_works":["https://openalex.org/W2390043387","https://openalex.org/W4210912933","https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4224287422","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3005560120"],"abstract_inverted_index":{"The":[0,64,186,226],"main":[1],"task":[2],"of":[3,68,82,198,213,245],"reinforcement":[4,30,56,129,223,239],"learning":[5,20,31,57,224,240],"is":[6,80,132,234],"to":[7,11,40,97,108,122,151,168,201,209,236],"enable":[8],"the":[9,13,17,42,49,73,90,99,105,109,115,119,123,137,144,149,165,173,179,189,196,199,206,211,214,231,243,246],"subject":[10],"obtain":[12],"most":[14],"reward":[15],"from":[16],"environment.":[18],"Reinforcement":[19],"has":[21],"been":[22],"proposed":[23,54,65,215,232],"and":[24,72,85,103,194,217],"achieved":[25],"certain":[26],"results.":[27],"However,":[28],"many":[29],"methods":[32,241],"still":[33],"have":[34],"inefficiencies":[35],"that":[36,230],"result":[37],"in":[38,44,242],"inability":[39],"meet":[41],"demand":[43],"some":[45,221,237],"applications.":[46],"Aiming":[47],"at":[48],"above":[50],"problems,":[51],"this":[52],"paper":[53,204],"a":[55],"algorithm":[58,150,200,233],"based":[59],"on":[60],"multi-subnet":[61],"cluster":[62,79,117,177],"(MSC-RL).":[63],"network":[66,167,182],"consists":[67],"multiple":[69,83,93],"subnet":[70,78,91,116,163,174],"clusters":[71],"primary":[74,124,180],"storage":[75,125,181],"network.":[76,88,111,126],"Each":[77,176],"composed":[81],"subnets":[84,94,146,193],"one":[86],"sub-storage":[87,110,166],"In":[89,127],"cluster,":[92],"are":[95],"used":[96],"explore":[98],"solution":[100],"space":[101],"simultaneously":[102],"saves":[104,118],"searched":[106,120,160],"information":[107,121,141,159,170,184,190],"At":[112],"regular":[113],"intervals,":[114],"traditional":[128],"learning,":[130],"there":[131],"not":[133],"enough":[134],"interaction":[135,142,171,191],"between":[136,143,192],"independent":[138,145],"subnets.":[139],"Insufficient":[140],"can":[147,157],"cause":[148],"fall":[152],"into":[153],"local":[154],"optimum.":[155],"MSC-RL":[156],"exchange":[158],"by":[161],"each":[162],"through":[164],"realize":[169],"within":[172],"cluster.":[175],"uses":[178,205],"for":[183],"interaction.":[185],"method":[187,216],"enhances":[188],"improves":[195],"ability":[197],"optimize.":[202],"This":[203],"Atari":[207,247],"game":[208],"verify":[210],"performance":[212,244],"compared":[218],"it":[219],"with":[220],"mainstream":[222,238],"methods.":[225],"experimental":[227],"results":[228],"show":[229],"superior":[235],"game.":[248]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}