{"id":"https://openalex.org/W4319302695","doi":"https://doi.org/10.1109/tcds.2023.3242274","title":"Alternated Greedy-Step Deterministic Policy Gradient","display_name":"Alternated Greedy-Step Deterministic Policy Gradient","publication_year":2023,"publication_date":"2023-02-06","ids":{"openalex":"https://openalex.org/W4319302695","doi":"https://doi.org/10.1109/tcds.2023.3242274"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2023.3242274","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tcds.2023.3242274","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-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/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101885863","display_name":"Jiazhi Zhang","orcid":"https://orcid.org/0009-0009-8963-6374"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Zhang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8963-6374","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732156","display_name":"Yang Gu","orcid":"https://orcid.org/0000-0002-6698-479X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gu","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6698-479X","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017591415","display_name":"Kun Yu","orcid":"https://orcid.org/0000-0001-7587-8027"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Yu","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-8027","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, the Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.3226,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61963314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"15","issue":"4","first_page":"2190","last_page":"2201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9836999773979187,"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/T12676","display_name":"Machine Learning and ELM","score":0.9836999773979187,"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/notation","display_name":"Notation","score":0.7482996582984924},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.46165192127227783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4293268024921417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4268219769001007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3923914134502411},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.33058643341064453},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1421985924243927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11100327968597412}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.7482996582984924},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46165192127227783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4293268024921417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4268219769001007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3923914134502411},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33058643341064453},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1421985924243927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11100327968597412}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2023.3242274","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tcds.2023.3242274","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6792490895","display_name":null,"funder_award_id":"61976215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8143754585","display_name":null,"funder_award_id":"BE2022095","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2080889016","https://openalex.org/W2093253120","https://openalex.org/W2145339207","https://openalex.org/W2469051754","https://openalex.org/W2595700172","https://openalex.org/W2740912559","https://openalex.org/W2746553466","https://openalex.org/W2959091704","https://openalex.org/W2978943496","https://openalex.org/W3000642679","https://openalex.org/W3006670279","https://openalex.org/W3016330197","https://openalex.org/W3097268408","https://openalex.org/W3114551027","https://openalex.org/W3170872007","https://openalex.org/W3171807757","https://openalex.org/W3174772619","https://openalex.org/W3203189308","https://openalex.org/W4205945022","https://openalex.org/W4206121515","https://openalex.org/W4206678833","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4323542458","https://openalex.org/W6602057636","https://openalex.org/W6637967152","https://openalex.org/W6677067356","https://openalex.org/W6684921986","https://openalex.org/W6735506055","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6771936881","https://openalex.org/W6776730770","https://openalex.org/W6790917506","https://openalex.org/W6796557232","https://openalex.org/W6802039951","https://openalex.org/W6802123420"],"related_works":["https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W4245490552","https://openalex.org/W4225152035","https://openalex.org/W2504004674","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W1587224694","https://openalex.org/W2911598644"],"abstract_inverted_index":{"The":[0,160],"greedy-step":[1,91,174],"<inline-formula":[2,13,29,38,59,73,100,130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3,14,30,39,60,74,101,131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[4,15,31,40,61,75,102,132],"<tex-math":[5,16,32,41,62,76,103,133],"notation=\"LaTeX\">$Q$":[6,17,33,42,63,77,104],"</tex-math></inline-formula>-learning":[7],"(GQL)":[8],"can":[9,126,180],"effectively":[10],"accelerate":[11],"the":[12,35,72,87,113,122,128,138,144,148,153,156,163,190,206],"</tex-math></inline-formula>-value":[18,43,64,78,105],"updating":[19],"process.":[20],"However,":[21],"since":[22],"it":[23],"is":[24,107,119,141,166,186],"an":[25,89,172],"improved":[26],"version":[27],"of":[28,37,97,155,162,200,205],"</tex-math></inline-formula>-learning,":[34],"problem":[36],"overestimation":[44],"also":[45],"exists.":[46],"Since":[47],"there":[48],"are":[49,81],"in":[50,65,109,168],"total":[51],"two":[52,98],"max":[53],"operators":[54],"used":[55],"to":[56,70,120,142,183],"iteratively":[57],"calculate":[58],"GQL,":[66],"many":[67],"existing":[68],"solutions":[69],"reduce":[71],"estimation":[79],"bias":[80],"invalid":[82],"for":[83],"GQL.":[84],"To":[85],"address":[86],"issue,":[88],"alternated":[90,173],"update":[92,143],"(AGU)":[93],"framework":[94,165,192],"that":[95,125,179],"consists":[96],"independent":[99],"estimators":[106],"proposed":[108,114,187],"this":[110],"study.":[111],"In":[112,170],"AGU":[115,164,191],"framework,":[116],"one":[117],"estimator":[118,140,146],"determine":[121],"time":[123,158],"step":[124],"maximize":[127],"estimated":[129],"notation=\"LaTeX\">$n$":[134],"</tex-math></inline-formula>-step":[135],"return":[136],"and":[137],"other":[139],"prior":[145],"using":[147],"target":[149],"value":[150],"calculated":[151],"on":[152,202],"basis":[154],"determined":[157],"step.":[159],"convergence":[161],"proved":[167],"theoretical.":[169],"addition,":[171],"deterministic":[175,195],"policy":[176,196],"gradient":[177,197],"(AGDPG)":[178],"be":[181],"applied":[182],"continuous-action":[184,203],"tasks":[185,204],"by":[188],"combining":[189],"with":[193],"deep":[194],"(DDPG).":[198],"Experiments":[199],"AGDPG":[201],"MuJoCo":[207],"platform":[208],"highlight":[209],"its":[210],"superior":[211],"performance.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}