{"id":"https://openalex.org/W4362580550","doi":"https://doi.org/10.1145/3590154","title":"GLDAP: Global Dynamic Action Persistence Adaptation for Deep Reinforcement Learning","display_name":"GLDAP: Global Dynamic Action Persistence Adaptation for Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-04-03","ids":{"openalex":"https://openalex.org/W4362580550","doi":"https://doi.org/10.1145/3590154"},"language":"en","primary_location":{"id":"doi:10.1145/3590154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3590154","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3590154&file=3590154-vor.pdf","source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3590154&file=3590154-vor.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078280733","display_name":"Junbo Tong","orcid":"https://orcid.org/0000-0002-7433-0788"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junbo Tong","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012434681","display_name":"Daming Shi","orcid":"https://orcid.org/0000-0001-8327-555X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daming Shi","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330660","display_name":"Yi Liu","orcid":"https://orcid.org/0009-0001-4797-7826"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693811","display_name":"Wenhui Fan","orcid":"https://orcid.org/0000-0002-0040-5759"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Fan","raw_affiliation_strings":["Department of Automation, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078280733"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6959,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74471373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"18","issue":"2","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9807000160217285,"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/T10260","display_name":"Software Engineering Research","score":0.9276999831199646,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9016374349594116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784614086151123},{"id":"https://openalex.org/keywords/persistence","display_name":"Persistence (discontinuity)","score":0.7229556441307068},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7220619916915894},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5811675190925598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49582919478416443},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4559917151927948},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43182867765426636},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4315210282802582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3653374910354614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10354670882225037}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9016374349594116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784614086151123},{"id":"https://openalex.org/C2781009140","wikidata":"https://www.wikidata.org/wiki/Q7170389","display_name":"Persistence (discontinuity)","level":2,"score":0.7229556441307068},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7220619916915894},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5811675190925598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49582919478416443},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4559917151927948},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43182867765426636},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4315210282802582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3653374910354614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10354670882225037},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C187320778","wikidata":"https://www.wikidata.org/wiki/Q1349130","display_name":"Geotechnical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3590154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3590154","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3590154&file=3590154-vor.pdf","source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3590154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3590154","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3590154&file=3590154-vor.pdf","source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362580550.pdf","grobid_xml":"https://content.openalex.org/works/W4362580550.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2073540225","https://openalex.org/W2081357360","https://openalex.org/W2109910161","https://openalex.org/W2184117900","https://openalex.org/W2260756217","https://openalex.org/W2319287212","https://openalex.org/W2575705757","https://openalex.org/W2598912124","https://openalex.org/W2602275733","https://openalex.org/W2605102581","https://openalex.org/W2612690371","https://openalex.org/W2768629321","https://openalex.org/W2913403708","https://openalex.org/W2999905431","https://openalex.org/W3157439125","https://openalex.org/W3195143297","https://openalex.org/W3211390666","https://openalex.org/W4214717370","https://openalex.org/W4298023569","https://openalex.org/W6684205842","https://openalex.org/W6759008790"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"In":[0],"the":[1,30,41,49,94,98,136,142],"implementation":[2],"of":[3,25,29,43,52,101,114,138],"deep":[4,81],"reinforcement":[5,44,82],"learning":[6,45],"(DRL),":[7],"action":[8,56,71,77,104,144],"persistence":[9,57,72,78,145],"strategies":[10],"are":[11],"often":[12],"adopted":[13],"so":[14],"agents":[15],"maintain":[16],"their":[17],"actions":[18,35],"for":[19,33,80],"a":[20,66,86],"fixed":[21],"or":[22],"variable":[23],"number":[24],"steps.":[26],"The":[27],"choice":[28],"persistent":[31],"duration":[32],"agent":[34],"usually":[36],"has":[37],"notable":[38],"effects":[39],"on":[40],"performance":[42,116],"algorithms.":[46],"Aiming":[47],"at":[48],"research":[50],"gap":[51],"global":[53,69,76],"dynamic":[54,70],"optimal":[55,143],"and":[58,97,118,130],"its":[59],"application":[60],"in":[61],"multi-agent":[62,131],"systems,":[63],"we":[64],"propose":[65],"novel":[67],"framework:":[68],"(GLDAP),":[73],"which":[74],"achieves":[75,111],"adaptation":[79],"learning.":[83],"We":[84,133],"introduce":[85],"closed-loop":[87],"method":[88],"that":[89,109],"is":[90],"used":[91],"to":[92,140],"learn":[93],"estimated":[95],"value":[96],"corresponding":[99],"policy":[100],"each":[102],"candidate":[103],"persistence.":[105],"Our":[106],"experiment":[107],"shows":[108],"GLDAP":[110,139],"an":[112],"average":[113],"2.5%~90.7%":[115],"improvement":[117],"3~20":[119],"times":[120],"higher":[121],"sampling":[122],"efficiency":[123],"over":[124],"several":[125],"baselines":[126],"across":[127],"various":[128],"single-agent":[129],"domains.":[132],"also":[134],"validate":[135],"ability":[137],"determine":[141],"through":[146],"multiple":[147],"experiments.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}