{"id":"https://openalex.org/W2968677062","doi":"https://doi.org/10.1145/3342999.3343012","title":"A Priority Experience Replay Sampling Method Based on Upper Confidence Bound","display_name":"A Priority Experience Replay Sampling Method Based on Upper Confidence Bound","publication_year":2019,"publication_date":"2019-07-05","ids":{"openalex":"https://openalex.org/W2968677062","doi":"https://doi.org/10.1145/3342999.3343012","mag":"2968677062"},"language":"en","primary_location":{"id":"doi:10.1145/3342999.3343012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342999.3343012","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 Deep Learning Technologies","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/A5065946952","display_name":"Fengkai Ke","orcid":"https://orcid.org/0000-0002-4761-5120"},"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":"Fengkai Ke","raw_affiliation_strings":["School of Mechanical Engineering, Hubei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Hubei University of Technology, China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100547840","display_name":"Daxing Zhao","orcid":null},"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":"Daxing Zhao","raw_affiliation_strings":["School of Mechanical Engineering, Hubei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Hubei University of Technology, China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071335561","display_name":"Guodong Sun","orcid":"https://orcid.org/0000-0002-6756-7007"},"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":"Guodong Sun","raw_affiliation_strings":["School of Mechanical Engineering, Hubei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Hubei University of Technology, China","institution_ids":["https://openalex.org/I74525822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044432126","display_name":"Wei Feng","orcid":"https://orcid.org/0000-0001-7472-7921"},"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":"Wei Feng","raw_affiliation_strings":["School of Mechanical Engineering, Hubei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Hubei University of Technology, China","institution_ids":["https://openalex.org/I74525822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065946952"],"corresponding_institution_ids":["https://openalex.org/I74525822"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12891557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9215999841690063,"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":0.8689662218093872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8087837100028992},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6911059617996216},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6577966809272766},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.5299922823905945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269031524658203},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5020051002502441},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49351203441619873},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.4914611577987671},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45549899339675903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32422828674316406},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14397281408309937},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08352279663085938},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.075702965259552}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8689662218093872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087837100028992},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6911059617996216},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6577966809272766},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.5299922823905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269031524658203},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5020051002502441},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49351203441619873},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.4914611577987671},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45549899339675903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32422828674316406},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14397281408309937},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08352279663085938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.075702965259552},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342999.3343012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342999.3343012","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 Deep Learning Technologies","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":40,"referenced_works":["https://openalex.org/W1488305092","https://openalex.org/W1641379095","https://openalex.org/W1718539190","https://openalex.org/W1821462560","https://openalex.org/W1969034465","https://openalex.org/W1982262386","https://openalex.org/W2039708501","https://openalex.org/W2043615441","https://openalex.org/W2085194340","https://openalex.org/W2097381042","https://openalex.org/W2102535283","https://openalex.org/W2107726111","https://openalex.org/W2113001609","https://openalex.org/W2117014758","https://openalex.org/W2141559645","https://openalex.org/W2144354855","https://openalex.org/W2145339207","https://openalex.org/W2156060469","https://openalex.org/W2161565164","https://openalex.org/W2168342951","https://openalex.org/W2183137222","https://openalex.org/W2365363856","https://openalex.org/W2548134372","https://openalex.org/W2556958149","https://openalex.org/W2582946978","https://openalex.org/W2764174595","https://openalex.org/W2767361967","https://openalex.org/W2770679144","https://openalex.org/W2782108898","https://openalex.org/W2793798239","https://openalex.org/W2802895140","https://openalex.org/W2884001105","https://openalex.org/W2907340087","https://openalex.org/W2949201811","https://openalex.org/W2951457461","https://openalex.org/W2963959137","https://openalex.org/W2964048876","https://openalex.org/W2970586779","https://openalex.org/W3000763545","https://openalex.org/W4250981202"],"related_works":["https://openalex.org/W2370014976","https://openalex.org/W2350399852","https://openalex.org/W3047864323","https://openalex.org/W4238714840","https://openalex.org/W2383809451","https://openalex.org/W2381368487","https://openalex.org/W2994963386","https://openalex.org/W2367020632","https://openalex.org/W2298795098","https://openalex.org/W2088812990"],"abstract_inverted_index":{"With":[0],"the":[1,10,31,34,42,53,60,76,79,97,101,105,115,120,126,132,139,144,152,159],"development":[2],"of":[3,14,30,36,44,57,75,78,104,122,128,158],"deep":[4,37],"learning":[5,12,16,39,68],"and":[6,23,25,48,69,108,125],"computer":[7],"computing":[8],"ability,":[9],"end-to-end":[11],"mechanism":[13,56],"reinforcement":[15,38,58],"gradually":[17],"shows":[18],"its":[19],"advantages":[20],"in":[21,67,100,131,151],"control":[22,155],"strategy":[24],"other":[26],"application":[27],"fields.":[28],"One":[29],"keys":[32],"to":[33,71,113,143],"success":[35],"comes":[40],"from":[41],"establishment":[43],"sample":[45,80,87],"experience":[46,49,54,91,102],"pool":[47,103],"replay":[50,55,92],"algorithm.":[51],"In":[52,82],"learning,":[59],"traditional":[61,106],"random":[62,98],"sampling":[63,88,99,133],"algorithm":[64,89,107,124,140],"is":[65,93,136],"inefficient":[66],"fails":[70],"make":[72],"full":[73],"use":[74],"information":[77],"itself.":[81],"this":[83],"paper,":[84],"a":[85,148],"new":[86],"for":[90],"proposed,":[94],"which":[95],"avoids":[96],"only":[109],"takes":[110],"some":[111],"time":[112],"train":[114],"samples":[116,129],"repeatedly.":[117],"By":[118],"integrating":[119],"characteristics":[121],"UCB":[123],"diversity":[127],"required":[130],"process,":[134],"it":[135],"proved":[137],"that":[138],"can":[141],"converge":[142],"optimal":[145],"solution":[146],"at":[147],"fast":[149],"speed":[150],"continuous":[153],"motion":[154],"grasping":[156],"experiment":[157],"mechanical":[160],"arm.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}