{"id":"https://openalex.org/W3010686966","doi":"https://doi.org/10.1109/sips47522.2019.9020610","title":"Memory Reduction through Experience Classification f or Deep Reinforcement Learning with Prioritized Experience Replay","display_name":"Memory Reduction through Experience Classification f or Deep Reinforcement Learning with Prioritized Experience Replay","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3010686966","doi":"https://doi.org/10.1109/sips47522.2019.9020610","mag":"3010686966"},"language":"en","primary_location":{"id":"doi:10.1109/sips47522.2019.9020610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips47522.2019.9020610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Workshop on Signal Processing Systems (SiPS)","raw_type":"proceedings-article"},"type":"article","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/A5060233511","display_name":"Kai-Huan Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kai-Huan Shen","raw_affiliation_strings":["Department of Electrical Engineering, National Central University, Jhong-Li, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Central University, Jhong-Li, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050419801","display_name":"Pei\u2010Yun Tsai","orcid":"https://orcid.org/0000-0002-6088-3875"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Yun Tsai","raw_affiliation_strings":["Department of Electrical Engineering, National Central University, Jhong-Li, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Central University, Jhong-Li, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060233511"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.1192,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50253939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"166","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9929999709129333,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.841533899307251},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7854936122894287},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6529620289802551},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.5926709771156311},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5550664067268372},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4784255623817444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47438982129096985},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46197569370269775},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3419908285140991},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2176274061203003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841533899307251},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7854936122894287},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6529620289802551},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.5926709771156311},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5550664067268372},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4784255623817444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47438982129096985},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46197569370269775},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3419908285140991},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2176274061203003},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips47522.2019.9020610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips47522.2019.9020610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Workshop on Signal Processing Systems (SiPS)","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":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2009303086","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2772721022","https://openalex.org/W2775482448","https://openalex.org/W2963864421","https://openalex.org/W3100789280","https://openalex.org/W4245108548","https://openalex.org/W4293872189","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6746809867"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2120821724","https://openalex.org/W2350715914","https://openalex.org/W2101175215","https://openalex.org/W2379529020","https://openalex.org/W2893549521","https://openalex.org/W1562157883","https://openalex.org/W2352322616","https://openalex.org/W2574438335"],"abstract_inverted_index":{"Prioritized":[0],"experience":[1,51],"replay":[2,23,80,129],"has":[3],"been":[4],"widely":[5],"used":[6,105],"in":[7,16,30,78,87,127],"many":[8],"online":[9],"reinforcement":[10],"learning":[11,133],"algorithms,":[12],"providing":[13],"high":[14],"efficiency":[15],"exploiting":[17],"past":[18],"experiences.":[19],"However,":[20],"a":[21,33,64],"large":[22],"buffer":[24,118],"consumes":[25],"system":[26],"storage":[27],"significantly.":[28],"Thus,":[29,131],"this":[31],"paper,":[32],"segmentation":[34],"and":[35,95,99,120],"classification":[36],"scheme":[37,84],"is":[38,47,55,70,85,139],"proposed.":[39],"The":[40,50,82],"distribution":[41],"of":[42,76,125,144,147],"temporal-difference":[43],"errors":[44],"(TD":[45],"errors)":[46],"first":[48],"segmented.":[49],"for":[52,67,106],"network":[53],"training":[54],"classified":[56],"according":[57],"to":[58,72],"its":[59],"updated":[60,148],"TD":[61,149],"error.":[62],"Then,":[63],"swap":[65],"mechanism":[66,113],"similar":[68],"experiences":[69,77,126],"implemented":[71],"change":[73],"the":[74,79,88,96,109,117,123,128,142],"lifetimes":[75],"buffer.":[81,130],"proposed":[83,112],"incorporated":[86],"Deep":[89],"Deterministic":[90],"Policy":[91],"Gradient":[92],"(DDPG)":[93],"algorithm,":[94],"Inverted":[97,100],"Pendulum":[98,102],"Double":[101],"tasks":[103],"are":[104],"verification.":[107],"From":[108],"experiments,":[110],"our":[111],"can":[114],"effectively":[115],"remove":[116],"redundancy":[119],"further":[121],"reduce":[122],"correlation":[124],"better":[132],"performance":[134],"with":[135],"reduced":[136],"memory":[137],"size":[138],"achieved":[140],"at":[141],"cost":[143],"additional":[145],"computations":[146],"errors.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}