{"id":"https://openalex.org/W2955251534","doi":"https://doi.org/10.1109/tcyb.2018.2853582","title":"Prioritizing Useful Experience Replay for Heuristic Dynamic Programming-Based Learning Systems","display_name":"Prioritizing Useful Experience Replay for Heuristic Dynamic Programming-Based Learning Systems","publication_year":2019,"publication_date":"2019-07-19","ids":{"openalex":"https://openalex.org/W2955251534","doi":"https://doi.org/10.1109/tcyb.2018.2853582","mag":"2955251534","pmid":"https://pubmed.ncbi.nlm.nih.gov/30059327"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2018.2853582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2853582","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5075006150","display_name":"Zhen Ni","orcid":"https://orcid.org/0000-0003-3166-4726"},"institutions":[{"id":"https://openalex.org/I177156846","display_name":"South Dakota State University","ror":"https://ror.org/015jmes13","country_code":"US","type":"education","lineage":["https://openalex.org/I177156846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Ni","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD, USA","institution_ids":["https://openalex.org/I177156846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055771665","display_name":"Naresh Malla","orcid":"https://orcid.org/0000-0002-8889-8833"},"institutions":[{"id":"https://openalex.org/I177156846","display_name":"South Dakota State University","ror":"https://ror.org/015jmes13","country_code":"US","type":"education","lineage":["https://openalex.org/I177156846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naresh Malla","raw_affiliation_strings":["Electrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD, USA","institution_ids":["https://openalex.org/I177156846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010882980","display_name":"X. Zhong","orcid":"https://orcid.org/0000-0002-8367-0215"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangnan Zhong","raw_affiliation_strings":["Electrical Engineering Department, University of North Texas, Denton, TX, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075006150"],"corresponding_institution_ids":["https://openalex.org/I177156846"],"apc_list":null,"apc_paid":null,"fwci":6.0138,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96748249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"49","issue":"11","first_page":"3911","last_page":"3922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007006645202637},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.6936689615249634},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5225012898445129},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4986867904663086},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.480782687664032},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4713532328605652},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4633951783180237},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4452876150608063},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4377587139606476},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4343520998954773},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43055811524391174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2916357219219208},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29141491651535034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1167079508304596},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08747947216033936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007006645202637},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.6936689615249634},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5225012898445129},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4986867904663086},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.480782687664032},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4713532328605652},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4633951783180237},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4452876150608063},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4377587139606476},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4343520998954773},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43055811524391174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2916357219219208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29141491651535034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1167079508304596},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08747947216033936},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2018.2853582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2853582","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:30059327","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30059327","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4974512343","display_name":null,"funder_award_id":"NNX15AK54A","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W624020015","https://openalex.org/W814391925","https://openalex.org/W1517236425","https://openalex.org/W1626155273","https://openalex.org/W1757796397","https://openalex.org/W1854776945","https://openalex.org/W1901616594","https://openalex.org/W1980620643","https://openalex.org/W1982262386","https://openalex.org/W1988688219","https://openalex.org/W2000029621","https://openalex.org/W2005675298","https://openalex.org/W2035832954","https://openalex.org/W2048226872","https://openalex.org/W2060605484","https://openalex.org/W2073591687","https://openalex.org/W2085194340","https://openalex.org/W2101879828","https://openalex.org/W2124829859","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2165501837","https://openalex.org/W2183137222","https://openalex.org/W2201581102","https://openalex.org/W2291165559","https://openalex.org/W2339745223","https://openalex.org/W2343701426","https://openalex.org/W2526096220","https://openalex.org/W2529203006","https://openalex.org/W2543834468","https://openalex.org/W2550302514","https://openalex.org/W2551113280","https://openalex.org/W2564818672","https://openalex.org/W2580175322","https://openalex.org/W2615522212","https://openalex.org/W2618682531","https://openalex.org/W2735102444","https://openalex.org/W2735449579","https://openalex.org/W2735850463","https://openalex.org/W2746553466","https://openalex.org/W2767784613","https://openalex.org/W2792596411","https://openalex.org/W2884970059","https://openalex.org/W2919115771","https://openalex.org/W2963095800","https://openalex.org/W2963477884","https://openalex.org/W3103456419","https://openalex.org/W3103559770","https://openalex.org/W3148685027","https://openalex.org/W4226336799","https://openalex.org/W4245108548","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6687681856","https://openalex.org/W6728025962","https://openalex.org/W6730111887","https://openalex.org/W6732665253"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2350715914","https://openalex.org/W2101175215","https://openalex.org/W2379529020","https://openalex.org/W2120821724","https://openalex.org/W2893549521","https://openalex.org/W2352322616","https://openalex.org/W2124140241","https://openalex.org/W2598699656"],"abstract_inverted_index":{"The":[0,98,144],"adaptive":[1],"dynamic":[2,55],"programming":[3,56],"controller":[4,96],"usually":[5],"needs":[6],"a":[7,59,79,107,112],"long":[8],"training":[9],"period":[10],"because":[11],"the":[12,21,38,69,75,86,122,136,140,148,169,191,194],"data":[13],"usage":[14],"efficiency":[15],"is":[16,33,65,82,101,187],"relatively":[17],"low":[18],"by":[19,156],"discarding":[20],"samples":[22],"once":[23],"used.":[24],"Prioritized":[25],"experience":[26],"replay":[27],"(ER)":[28],"promotes":[29],"important":[30],"experiences":[31],"and":[32,91,111,127,135,160],"more":[34],"efficient":[35,46],"in":[36,166],"learning":[37,47],"control":[39,196],"process.":[40],"This":[41],"paper":[42],"proposes":[43],"integrating":[44],"an":[45],"capability":[48],"of":[49,94,152,178,193],"prioritized":[50],"ER":[51,70,87],"design":[52,68],"into":[53,88],"heuristic":[54],"(HDP).":[57],"First,":[58],"one":[60],"time-step":[61],"backward":[62],"state-action":[63],"pair":[64],"used":[66],"to":[67,84,154,189],"tuple":[71],"and,":[72],"thus,":[73],"avoids":[74],"model":[76],"network.":[77],"Second,":[78],"systematic":[80],"approach":[81,100,138,146],"proposed":[83,99,137,145,195],"integrate":[85],"both":[89,132],"critic":[90],"action":[92],"networks":[93],"HDP":[95,134,171,180],"design.":[97,197],"tested":[102],"for":[103,131,158,162,181],"two":[104],"case":[105],"studies:":[106],"cart-pole":[108],"balancing":[109,115,164],"task":[110],"triple-link":[113,163],"pendulum":[114],"task.":[116],"For":[117],"fair":[118],"comparison,":[119],"we":[120,174],"set":[121],"same":[123,141],"initial":[124,128],"weight":[125],"parameters":[126],"starting":[129],"states":[130],"traditional":[133,170],"under":[139],"simulation":[142],"environment.":[143],"improves":[147],"required":[149],"average":[150],"number":[151],"trials":[153],"succeed":[155],"60.56%":[157],"cart-pole,":[159],"56.89%":[161],"tasks,":[165],"comparison":[167],"with":[168],"approach.":[172],"Also,":[173],"have":[175],"added":[176],"results":[177],"ER-based":[179],"comparison.":[182],"Moreover,":[183],"theoretical":[184],"convergence":[185],"analysis":[186],"presented":[188],"guarantee":[190],"stability":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}