{"id":"https://openalex.org/W4317383042","doi":"https://doi.org/10.1109/robio55434.2022.10011801","title":"Leveraging Efficiency through Hybrid Prioritized Experience Replay in Door Environment","display_name":"Leveraging Efficiency through Hybrid Prioritized Experience Replay in Door Environment","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383042","doi":"https://doi.org/10.1109/robio55434.2022.10011801"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011801","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011801","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"https://openalex.org/A5071856936","display_name":"Haofu Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofu Qian","raw_affiliation_strings":["Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","Ocean College, Zhejiang University, Zhoushan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109646818","display_name":"Shiqiang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqiang Zhu","raw_affiliation_strings":["Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","Ocean College, Zhejiang University, Zhoushan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022459286","display_name":"Hongjiang Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongjiang Ge","raw_affiliation_strings":["Hangzhou Steam Turbine Co. Ltd,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Steam Turbine Co. Ltd,Hangzhou,China,310000","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058116300","display_name":"Haolei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123181","display_name":"Zhoushan Institute of Calibration for Quality and Technology Supervision","ror":"https://ror.org/02kwn0g61","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210123181"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolei Shi","raw_affiliation_strings":["Zhoushan Institute of Calibration and Testing for Qualitative and Tech-nical Supervision,Zhoushan,China,316000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhoushan Institute of Calibration and Testing for Qualitative and Tech-nical Supervision,Zhoushan,China,316000","institution_ids":["https://openalex.org/I4210123181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030317245","display_name":"Jianfeng Liao","orcid":"https://orcid.org/0000-0002-4914-4457"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Liao","raw_affiliation_strings":["Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074371475","display_name":"Wei Song","orcid":"https://orcid.org/0000-0002-0828-7486"},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","Ocean College, Zhejiang University, Zhoushan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100562972","display_name":"Jianjun Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjun Gu","raw_affiliation_strings":["Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics, Research Institute of Interdisci-plinary Innovation, Zhejiang Lab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"123","issue":null,"first_page":"1439","last_page":"1444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9941999912261963,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9883000254631042,"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/computer-science","display_name":"Computer science","score":0.8519501686096191},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7096125483512878},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6358232498168945},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.555662214756012},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.45567023754119873},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4301499128341675},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3539522886276245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3454642593860626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519501686096191},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7096125483512878},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6358232498168945},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.555662214756012},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.45567023754119873},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4301499128341675},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3539522886276245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3454642593860626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011801","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011801","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":43,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W2145339207","https://openalex.org/W2159420891","https://openalex.org/W2165150801","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2761873684","https://openalex.org/W2775482448","https://openalex.org/W2786928559","https://openalex.org/W2788862220","https://openalex.org/W2806690340","https://openalex.org/W2877093712","https://openalex.org/W2895626374","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2905606790","https://openalex.org/W2908064123","https://openalex.org/W2908643158","https://openalex.org/W2963092423","https://openalex.org/W2963095800","https://openalex.org/W2963411833","https://openalex.org/W2964048876","https://openalex.org/W2964053787","https://openalex.org/W2965870268","https://openalex.org/W2975909688","https://openalex.org/W2990747716","https://openalex.org/W3021708257","https://openalex.org/W3028830971","https://openalex.org/W3113358868","https://openalex.org/W3115474368","https://openalex.org/W3126321819","https://openalex.org/W3127561923","https://openalex.org/W4214717370","https://openalex.org/W4226067323","https://openalex.org/W4287634727","https://openalex.org/W4288267481","https://openalex.org/W6683452725","https://openalex.org/W6696324988","https://openalex.org/W6744838376","https://openalex.org/W6748645729","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W3103325625","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2353602216","https://openalex.org/W1486898455"],"abstract_inverted_index":{"Experience":[0,119],"replay":[1,59,79,211],"enables":[2],"agents":[3,48],"to":[4,41,88,102,122,155,164,207],"remember":[5],"and":[6,31,127,139,166,184,204],"reuse":[7],"past":[8,19],"experiences":[9],"in":[10,64,170],"reinforcement":[11],"learning,":[12],"just":[13],"as":[14,78],"human":[15],"beings":[16],"utilize":[17],"the":[18,23,33,42,46,56,65,94,124,129,133,140,159,181,196,202],"memory.":[20],"At":[21],"present,":[22],"experience":[24,101,210],"buffer":[25],"of":[26,35,45,55,93],"on-policy":[27,208],"algorithm":[28,209],"iterates":[29],"fast":[30],"cause":[32],"problem":[34],"low":[36,43],"sample":[37,125],"utilization,":[38],"which":[39,68,86,132],"leads":[40,87],"efficiency":[44,203],"training":[47,182],"based":[49],"on":[50],"uniform":[51],"selected":[52],"samples.":[53],"Most":[54],"existing":[57],"rule-based":[58],"strategies":[60],"have":[61,69,82],"been":[62],"applied":[63],"off-policy":[66],"algorithm,":[67],"shown":[70],"good":[71],"results.":[72],"Replay":[73,120],"strategy":[74],"adjustment":[75],"is":[76,98],"challenging,":[77],"memory":[80],"samples":[81],"large":[83],"noise":[84],"levels,":[85],"unstable":[89],"value":[90],"functions.":[91],"One":[92],"most":[95],"challenging":[96],"aspects":[97],"deciding":[99],"what":[100],"prioritize.":[103],"To":[104],"solve":[105],"this":[106,199],"problem,":[107],"we":[108,190],"propose":[109,191],"a":[110,192],"method":[111,178,200],"called":[112],"Proximal":[113],"Policy":[114],"Optimization":[115],"with":[116],"Hybrid":[117],"Prioritized":[118],"(HPER-PPO)":[121],"adjust":[123],"priority":[126],"guide":[128],"selection,":[130],"through":[131],"policy":[134],"can":[135,143,179],"be":[136,144],"better":[137,156],"optimized":[138],"cumulative":[141,168],"reward":[142],"maximized.":[145],"We":[146],"select":[147],"two":[148],"kinds":[149],"door-":[150],"related":[151],"long":[152],"horizon":[153],"tasks":[154],"measure":[157],"whether":[158],"agent":[160],"has":[161],"greater":[162],"ability":[163],"learn":[165],"obtain":[167],"rewards":[169],"our":[171,177],"method.":[172],"The":[173],"results":[174],"show":[175],"that":[176],"reduce":[180],"time":[183],"potentially":[185],"increase":[186],"long-term":[187],"return.":[188],"Further,":[189],"possible":[193],"explanation":[194],"for":[195],"reason":[197],"why":[198],"improves":[201],"brings":[205],"changes":[206],"mechanism.":[212]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}