{"id":"https://openalex.org/W2775482448","doi":"https://doi.org/10.1109/smc.2017.8122622","title":"A novel DDPG method with prioritized experience replay","display_name":"A novel DDPG method with prioritized experience replay","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2775482448","doi":"https://doi.org/10.1109/smc.2017.8122622","mag":"2775482448"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2017.8122622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2017.8122622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5062441362","display_name":"Yuenan Hou","orcid":"https://orcid.org/0000-0002-2844-7416"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuenan Hou","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720047","display_name":"Lifeng Liu","orcid":"https://orcid.org/0000-0002-2384-6506"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Liu","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645169","display_name":"Qing Wei","orcid":"https://orcid.org/0000-0002-2860-9198"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wei","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101449188","display_name":"Xudong Xu","orcid":"https://orcid.org/0009-0005-6788-1759"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Xu","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":239,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T13553","display_name":"Age of Information Optimization","score":0.992900013923645,"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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9918000102043152,"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":0.7770020961761475},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6664401292800903},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6296941041946411},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6115518808364868},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5284968018531799},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5277341604232788},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34107905626296997},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2838352918624878},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13533657789230347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10419318079948425},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10265100002288818},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.06218379735946655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770020961761475},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6664401292800903},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6296941041946411},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6115518808364868},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5284968018531799},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5277341604232788},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34107905626296997},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2838352918624878},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13533657789230347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10419318079948425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10265100002288818},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.06218379735946655},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2017.8122622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2017.8122622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1570792896","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W1836465849","https://openalex.org/W1982262386","https://openalex.org/W2017814058","https://openalex.org/W2017957151","https://openalex.org/W2043106712","https://openalex.org/W2048226872","https://openalex.org/W2059836092","https://openalex.org/W2107741520","https://openalex.org/W2117941808","https://openalex.org/W2121863487","https://openalex.org/W2127830251","https://openalex.org/W2128609675","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2271840356","https://openalex.org/W2949117887","https://openalex.org/W2953384591","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964006217","https://openalex.org/W2964121744","https://openalex.org/W3037207827","https://openalex.org/W3101558632","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6635465357","https://openalex.org/W6639949747","https://openalex.org/W6676320248","https://openalex.org/W6682314434","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6713134421","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W2775233965","https://openalex.org/W4318559728","https://openalex.org/W4360995913","https://openalex.org/W4312193868","https://openalex.org/W4308165509"],"abstract_inverted_index":{"Recently,":[0],"a":[1,45],"state-of-the-art":[2],"algorithm,":[3,55],"called":[4],"deep":[5],"deterministic":[6],"policy":[7],"gradient":[8],"(DDPG),":[9],"has":[10],"achieved":[11],"good":[12],"performance":[13],"in":[14,19,33,42],"many":[15],"continuous":[16],"control":[17],"tasks":[18],"the":[20,26,29,39,53,94,99,102,110,117,124,128],"MuJoCo":[21],"simulator.":[22],"To":[23],"further":[24],"improve":[25,98],"efficiency":[27],"of":[28,62,101,112,119,127],"experience":[30,47,70,90],"replay":[31,48,71,91,120],"mechanism":[32],"DDPG":[34,54,67,87],"and":[35,97,105,123],"thus":[36],"speeding":[37],"up":[38],"training":[40,95,103],"process,":[41,104],"this":[43],"paper,":[44],"prioritized":[46,57,69,89],"method":[49],"is":[50,59,72,106],"proposed":[51,66],"for":[52],"where":[56],"sampling":[58],"adopted":[60],"instead":[61],"uniform":[63],"sampling.":[64],"The":[65,82],"with":[68,74,88],"tested":[73],"an":[75],"inverted":[76],"pendulum":[77],"task":[78],"via":[79],"OpenAI":[80],"Gym.":[81],"experimental":[83],"results":[84],"show":[85],"that":[86],"can":[92],"reduce":[93],"time":[96],"stability":[100],"less":[107],"sensitive":[108],"to":[109],"changes":[111],"some":[113],"hyperparameters":[114],"such":[115],"as":[116],"size":[118],"buffer,":[121],"minibatch":[122],"updating":[125],"rate":[126],"target":[129],"network.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}