{"id":"https://openalex.org/W4406947029","doi":"https://doi.org/10.1109/lra.2025.3536291","title":"Delayed Dynamic Model Scheduled Reinforcement Learning With Time-Varying Delays for Robotic Control","display_name":"Delayed Dynamic Model Scheduled Reinforcement Learning With Time-Varying Delays for Robotic Control","publication_year":2025,"publication_date":"2025-01-29","ids":{"openalex":"https://openalex.org/W4406947029","doi":"https://doi.org/10.1109/lra.2025.3536291"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3536291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3536291","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5104235748","display_name":"Zechang Wang","orcid":"https://orcid.org/0000-0001-9078-7270"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zechang Wang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684094","display_name":"Dengpeng Xing","orcid":"https://orcid.org/0000-0002-8251-9118"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengpeng Xing","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041434096","display_name":"Yiming Yang","orcid":"https://orcid.org/0000-0003-1359-0364"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011130586","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-8265-9866"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104235748"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89318239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":"3","first_page":"2646","last_page":"2653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9819999933242798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7958221435546875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5981655120849609},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5134614109992981},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.32988440990448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2940506339073181},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20243951678276062}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7958221435546875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5981655120849609},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5134614109992981},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32988440990448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2940506339073181},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20243951678276062}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3536291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3536291","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4102930997","display_name":null,"funder_award_id":"62073324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1980722163","https://openalex.org/W1986278286","https://openalex.org/W2105369176","https://openalex.org/W2117864026","https://openalex.org/W2158782408","https://openalex.org/W2159566498","https://openalex.org/W2897445793","https://openalex.org/W3154264273","https://openalex.org/W3195689706","https://openalex.org/W3203259721","https://openalex.org/W4399546722","https://openalex.org/W6684921986","https://openalex.org/W6747473740","https://openalex.org/W6755575430","https://openalex.org/W6788773875","https://openalex.org/W6789246195","https://openalex.org/W6852886635","https://openalex.org/W6860943719"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"typically":[3],"presupposes":[4],"instantaneous":[5],"agent-environment":[6],"interactions,":[7],"but":[8],"in":[9,120,141,162,191,202],"real-world":[10,30],"scenarios":[11,203],"such":[12,148],"as":[13],"robotic":[14,214],"control,":[15],"overlooking":[16],"observation":[17,207],"delays":[18],"can":[19],"significantly":[20],"impair":[21],"performance.":[22],"While":[23],"existing":[24,91],"studies":[25],"consider":[26],"stationary,":[27],"known":[28],"delays,":[29,64,208],"applications":[31],"frequently":[32],"encounter":[33],"unpredictable":[34],"delay":[35,58,100,110,115,142,164,189],"variations.":[36],"To":[37,134,172],"address":[38],"this":[39,41],"problem,":[40],"letter":[42],"presents":[43],"a":[44,71,167],"novel":[45],"algorithm":[46],"for":[47,213],"scheduling":[48],"delayed":[49,73,79,128],"dynamic":[50,74,129],"models.":[51],"Specifically,":[52],"We":[53],"propose":[54,107],"using":[55],"multiple":[56],"truncated":[57],"distributions":[59,119],"to":[60,69,84,94,103,113,131,147,156,185],"effectively":[61],"model":[62,130],"time-varying":[63,188],"with":[65,90],"each":[66],"distribution":[67,143,165],"tailored":[68],"learn":[70],"specific":[72],"model.":[75],"These":[76],"models":[77],"map":[78],"observations":[80],"and":[81,116,144],"historical":[82],"actions":[83],"the":[85,99,104,125,163,173,181,186,196],"current":[86],"state,":[87],"integrating":[88],"seamlessly":[89],"RL":[92],"algorithms":[93],"facilitate":[95],"optimal":[96],"decision-making.":[97],"Since":[98],"is":[101,180],"unknown":[102],"agent,":[105],"we":[106,150],"an":[108],"effective":[109,183],"estimation":[111],"method":[112,201],"detect":[114],"their":[117],"corresponding":[118],"real-time,":[121],"thereby":[122],"adaptively":[123],"selecting":[124],"most":[126],"appropriate":[127],"manage":[132],"delays.":[133],"reduce":[135],"instability":[136],"caused":[137],"by":[138,205],"abrupt":[139],"changes":[140],"enhance":[145],"responsiveness":[146],"variations,":[149],"apply":[151],"Bayesian":[152],"online":[153],"changepoint":[154],"detection":[155],"enable":[157],"rapid":[158],"sensing":[159],"of":[160,170,175,199],"alterations":[161],"within":[166],"finite":[168],"number":[169],"time-steps.":[171],"best":[174],"our":[176,178,200],"knowledge,":[177],"approach":[179],"first":[182],"solution":[184],"non-stationary":[187,206],"problem":[190],"RL.":[192],"Empirical":[193],"results":[194],"demonstrate":[195],"robust":[197],"performance":[198],"characterized":[204],"highlighting":[209],"its":[210],"strong":[211],"potential":[212],"control":[215],"applications.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}