{"id":"https://openalex.org/W3160587901","doi":"https://doi.org/10.1109/csicc52343.2021.9420550","title":"Duplicated Replay Buffer for Asynchronous Deep Deterministic Policy Gradient","display_name":"Duplicated Replay Buffer for Asynchronous Deep Deterministic Policy Gradient","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3160587901","doi":"https://doi.org/10.1109/csicc52343.2021.9420550","mag":"3160587901"},"language":"en","primary_location":{"id":"doi:10.1109/csicc52343.2021.9420550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc52343.2021.9420550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","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/A5012299359","display_name":"Seyed Mohammad Seyed Motehayeri","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Seyed Mohammad Seyed Motehayeri","raw_affiliation_strings":["University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064550357","display_name":"Vahid Baghi","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Vahid Baghi","raw_affiliation_strings":["University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051642756","display_name":"Ehsan Maani Miandoab","orcid":"https://orcid.org/0000-0002-2732-1088"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ehsan Maani Miandoab","raw_affiliation_strings":["University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101930446","display_name":"Ali Moeini","orcid":"https://orcid.org/0000-0002-6408-3525"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ali Moeini","raw_affiliation_strings":["University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59746279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9886000156402588,"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/T12288","display_name":"Optimization and Search Problems","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.863434374332428},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7165565490722656},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6117018461227417},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5910348892211914},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.584761917591095},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5502826571464539},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4831330478191376},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.340800940990448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33370018005371094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2152320146560669},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14413121342658997},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1401461958885193},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12662538886070251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863434374332428},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7165565490722656},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6117018461227417},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5910348892211914},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.584761917591095},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5502826571464539},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4831330478191376},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.340800940990448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33370018005371094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2152320146560669},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14413121342658997},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1401461958885193},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12662538886070251},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csicc52343.2021.9420550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc52343.2021.9420550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","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":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2558738305","https://openalex.org/W2741122588","https://openalex.org/W2746553466","https://openalex.org/W2775482448","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2889987506","https://openalex.org/W2910509260","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2989598077","https://openalex.org/W2998069546","https://openalex.org/W3011120880","https://openalex.org/W3106012737","https://openalex.org/W4287758406","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6683195989","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6730344819","https://openalex.org/W6738796088","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6753526802","https://openalex.org/W6770407973","https://openalex.org/W6772496516","https://openalex.org/W6779101081"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2150611273","https://openalex.org/W4306904969","https://openalex.org/W4207086172","https://openalex.org/W2042919702","https://openalex.org/W4225981436","https://openalex.org/W2156185805","https://openalex.org/W3204459944"],"abstract_inverted_index":{"Off-Policy":[0],"Deep":[1,8],"Reinforcement":[2],"Learning":[3],"(DRL)":[4],"algorithms":[5,76],"such":[6],"as":[7,49],"Deterministic":[9],"Policy":[10],"Gradient":[11],"(DDPG)":[12],"has":[13],"been":[14,31],"used":[15],"to":[16,20,34,52,80,88,165,184,196],"teach":[17],"intelligent":[18],"agents":[19],"solve":[21],"complicated":[22],"problems":[23],"in":[24,120,148],"continuous":[25],"space-action":[26],"environments.":[27],"Several":[28],"methods":[29],"have":[30,125],"successfully":[32],"applied":[33],"increase":[35],"the":[36,59,90,98,105,142,150,155,170,175,197,202],"training":[37,143],"performance":[38,187],"and":[39,43,77,154,168,174,188,212],"achieve":[40],"better":[41,113,186],"speed":[42],"stability":[44],"for":[45,74],"these":[46,75,82],"algorithms.":[47],"Such":[48],"experience":[50],"replay":[51,60,106,133,152,157,172,177],"selecting":[53,101],"a":[54,72,115,131,162],"batch":[55],"of":[56,58,100,201],"transactions":[57,103,145],"memory":[61,107,134],"buffer.":[62,108,158,178],"However,":[63],"working":[64],"with":[65,67,114,122,206],"environments":[66,123],"sparse":[68,116,207],"reward":[69,117,208],"function":[70,118],"is":[71],"challenge":[73],"causes":[78],"them":[79],"reduce":[81],"algorithms'":[83],"performance.":[84],"This":[85,179],"research":[86],"intends":[87],"make":[89],"transaction":[91],"selection":[92],"process":[93],"more":[94,138],"efficient":[95],"by":[96],"increasing":[97],"likelihood":[99],"important":[102],"from":[104],"Our":[109],"proposed":[110,194],"method":[111,180],"works":[112],"or,":[119],"particular,":[121],"that":[124,136],"termination":[126],"conditions.":[127],"We":[128,159],"are":[129,146],"using":[130],"secondary":[132,156,176],"buffer":[135,153,173],"stores":[137],"critical":[139],"transactions.":[140],"In":[141],"process,":[144],"select":[147],"both":[149],"first":[151],"also":[160],"use":[161],"parallel":[163],"environment":[164],"asynchronously":[166],"execute":[167],"fill":[169],"primary":[171],"will":[181],"help":[182],"us":[183],"get":[185],"stability.":[189],"Finally,":[190],"we":[191],"evaluate":[192],"our":[193],"approach":[195],"Crawler":[198],"model,":[199],"one":[200],"Unity":[203],"ML-Agent":[204],"tasks":[205],"function,":[209],"against":[210],"DDPG":[211],"AE-DDPG.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
