{"id":"https://openalex.org/W3185109031","doi":"https://doi.org/10.1109/access.2021.3097357","title":"Trajectory Based Prioritized Double Experience Buffer for Sample-Efficient Policy Optimization","display_name":"Trajectory Based Prioritized Double Experience Buffer for Sample-Efficient Policy Optimization","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3185109031","doi":"https://doi.org/10.1109/access.2021.3097357","mag":"3185109031"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3097357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3097357","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09486881.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09486881.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009030121","display_name":"Shengxiang Li","orcid":"https://orcid.org/0000-0001-5948-4634"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Li","raw_affiliation_strings":["College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5948-4634","affiliations":[{"raw_affiliation_string":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114767858","display_name":"Ou Li","orcid":"https://orcid.org/0000-0001-9807-9543"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ou Li","raw_affiliation_strings":["College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737337","display_name":"Guangyi Liu","orcid":"https://orcid.org/0000-0003-4241-508X"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyi Liu","raw_affiliation_strings":["College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106670735","display_name":"Siyuan Ding","orcid":"https://orcid.org/0009-0005-9496-5229"},"institutions":[{"id":"https://openalex.org/I4210145278","display_name":"Institute of Applied Physics and Computational Mathematics","ror":"https://ror.org/03sxpbt26","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Ding","raw_affiliation_strings":["Key Laboratory of Experimental Physics and Computational Mathematics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Experimental Physics and Computational Mathematics, Beijing, China","institution_ids":["https://openalex.org/I4210145278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027975656","display_name":"Yijie Bai","orcid":"https://orcid.org/0000-0001-8739-2454"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Bai","raw_affiliation_strings":["College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5459,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72065904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"101424","last_page":"101432"},"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":0.9890999794006348,"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":0.9797999858856201,"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":0.8860644698143005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8301621675491333},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6813250184059143},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6167615652084351},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6107411980628967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.432706356048584},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4119845926761627},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36334526538848877},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3224841058254242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08858627080917358}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8860644698143005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301621675491333},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6813250184059143},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6167615652084351},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6107411980628967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.432706356048584},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4119845926761627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36334526538848877},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3224841058254242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08858627080917358},{"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},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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":2,"locations":[{"id":"doi:10.1109/access.2021.3097357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3097357","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09486881.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:96cd240e3f3847f0aa2877d1d5286d0d","is_oa":true,"landing_page_url":"https://doaj.org/article/96cd240e3f3847f0aa2877d1d5286d0d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 101424-101432 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3097357","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3097357","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09486881.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3185109031.pdf","grobid_xml":"https://content.openalex.org/works/W3185109031.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1499669280","https://openalex.org/W1522301498","https://openalex.org/W1658008008","https://openalex.org/W1771410628","https://openalex.org/W2075268401","https://openalex.org/W2092710777","https://openalex.org/W2145339207","https://openalex.org/W2150234726","https://openalex.org/W2155027007","https://openalex.org/W2156347136","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2475089067","https://openalex.org/W2616729100","https://openalex.org/W2736601468","https://openalex.org/W2786036274","https://openalex.org/W2786928559","https://openalex.org/W2946120555","https://openalex.org/W2952227249","https://openalex.org/W2953334758","https://openalex.org/W2962941327","https://openalex.org/W2963296584","https://openalex.org/W2963477884","https://openalex.org/W2963674921","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2982316857","https://openalex.org/W2996031640","https://openalex.org/W3046988891","https://openalex.org/W4255783720","https://openalex.org/W4297797010","https://openalex.org/W6627932998","https://openalex.org/W6629881138","https://openalex.org/W6631190155","https://openalex.org/W6636881020","https://openalex.org/W6638018090","https://openalex.org/W6681980492","https://openalex.org/W6683001934","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6715102896","https://openalex.org/W6721101288","https://openalex.org/W6738174457","https://openalex.org/W6741002519","https://openalex.org/W6748554570","https://openalex.org/W6748638692","https://openalex.org/W6762717864","https://openalex.org/W6770580189","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W3131574667","https://openalex.org/W2586732548","https://openalex.org/W4323768008"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,27,115],"has":[2,29],"recently":[3],"made":[4],"great":[5],"progress":[6],"in":[7,40,55,94,104],"various":[8],"challenging":[9],"domains":[10],"such":[11],"as":[12],"board":[13],"game":[14,19],"of":[15,20,84,117],"Go":[16],"and":[17,37,42,53,64,90,122,134],"MOBA":[18],"StarCraft":[21],"II.":[22],"Policy":[23],"gradient":[24,47,74],"based":[25,86],"reinforcement":[26,114],"method":[28,75,111,129],"become":[30],"the":[31,78,92,113,123,127],"mainstream":[32],"due":[33],"to":[34,61,76],"its":[35],"effectiveness":[36],"simplicity":[38],"both":[39],"discrete":[41],"continuous":[43],"scenarios.":[44],"However,":[45],"policy":[46,73],"methods":[48],"commonly":[49],"involve":[50],"function":[51],"approximation":[52],"work":[54],"an":[56],"on-policy":[57],"fashion,":[58],"which":[59],"leads":[60],"high":[62],"variance":[63,93],"low":[65],"sample":[66,79],"efficiency.":[67],"This":[68],"paper":[69],"introduces":[70],"a":[71,82,97,105],"novel":[72],"improve":[77],"efficiency":[80],"via":[81],"pair":[83],"trajectory":[85],"prioritized":[87],"replay":[88],"buffers":[89],"reduce":[91],"training":[95],"with":[96],"target":[98],"network":[99],"whose":[100],"weights":[101],"are":[102],"updated":[103],"\u201csoft\u201d":[106],"manner.":[107],"We":[108],"evaluate":[109],"our":[110],"on":[112],"suit":[116],"Open":[118],"AI":[119],"Gym":[120],"tasks,":[121],"results":[124],"show":[125],"that":[126],"proposed":[128],"can":[130],"learn":[131],"more":[132],"steadily":[133],"achieve":[135],"higher":[136],"performance":[137],"than":[138],"existing":[139],"methods.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}