{"id":"https://openalex.org/W4399658607","doi":"https://doi.org/10.1145/3641584.3641781","title":"Improvement of prioritized experience replay mechanism based on deep deterministic policy gradient algorithm","display_name":"Improvement of prioritized experience replay mechanism based on deep deterministic policy gradient algorithm","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4399658607","doi":"https://doi.org/10.1145/3641584.3641781"},"language":"en","primary_location":{"id":"doi:10.1145/3641584.3641781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","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/A5074806344","display_name":"X. Zhang","orcid":"https://orcid.org/0009-0005-9607-573X"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0005-9607-573X","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043864588","display_name":"Y.C. Xu","orcid":"https://orcid.org/0009-0004-5937-4514"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihuan Xu","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0004-5937-4514","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"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":null,"issue":null,"first_page":"1310","last_page":"1316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.951200008392334,"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":0.951200008392334,"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":0.9065999984741211,"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":0.7699269652366638},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5623844861984253},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5424308776855469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699269652366638},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5623844861984253},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5424308776855469},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641584.3641781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","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":8,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1982262386","https://openalex.org/W2043106712","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2775482448","https://openalex.org/W4245108548","https://openalex.org/W7103655332"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,14,23,32,55,61,67,74,79,86,96,106],"problem":[4,56,84],"of":[5,16,35,57,60],"inefficient":[6],"sampling":[7,19,107],"in":[8],"deep":[9,98],"reinforcement":[10],"learning":[11],"and":[12,66,85,109],"investigates":[13],"feasibility":[15],"using":[17,37],"prioritized":[18,38,62],"methods":[20],"based":[21,46],"on":[22,47],"Deep":[24],"Deterministic":[25],"Policy":[26],"Gradient":[27],"algorithm":[28,70,77],"(DDPG)":[29],"to":[30,53],"accelerate":[31],"training":[33,112],"process":[34],"DDPG":[36,69,76],"experience":[39,63],"replay.":[40],"A":[41],"small":[42],"sample":[43,48],"sorting":[44],"method":[45,102],"priority":[49],"is":[50,71],"also":[51],"proposed":[52],"solve":[54],"high":[58],"complexity":[59],"replay":[64],"algorithm,":[65],"original":[68],"compared":[72],"with":[73],"improved":[75,97],"through":[78],"classical":[80],"inverted":[81],"pendulum":[82],"control":[83],"trained":[87],"robot":[88],"unipedal":[89],"jump":[90],"problem.":[91],"The":[92],"results":[93],"show":[94],"that":[95],"deterministic":[99],"policy":[100],"gradient":[101],"can":[103],"significantly":[104],"improve":[105],"efficiency":[108],"has":[110],"better":[111],"results.":[113]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}