{"id":"https://openalex.org/W7150981847","doi":"https://doi.org/10.1109/lra.2026.3681154","title":"Safe Policy Optimization With Cost Practical Stability: A DQ-Learning Method","display_name":"Safe Policy Optimization With Cost Practical Stability: A DQ-Learning Method","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7150981847","doi":"https://doi.org/10.1109/lra.2026.3681154"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3681154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3681154","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":null,"display_name":"Chenyu Wang","orcid":"https://orcid.org/0009-0004-7182-2164"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenyu Wang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-7182-2164","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linkai Liu","orcid":"https://orcid.org/0009-0004-1988-7008"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linkai Liu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1988-7008","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058029021","display_name":"Quan Quan","orcid":"https://orcid.org/0000-0001-8216-8998"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Quan","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8216-8998","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77810406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"6","first_page":"6823","last_page":"6830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42329999804496765,"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":0.42329999804496765,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.2240999937057495,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.020099999383091927,"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/key","display_name":"Key (lock)","score":0.3068999946117401},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.29170000553131104},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2662999927997589},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.2599000036716461},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.25360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5138000249862671},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2623000144958496},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3681154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3681154","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/G5343775","display_name":null,"funder_award_id":"62573021","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Safety":[0],"is":[1],"a":[2,38,54,65,94,105],"critical":[3],"requirement":[4],"in":[5,11,117],"robotics,":[6],"leading":[7],"to":[8,22,73],"extensive":[9],"research":[10],"Safe":[12],"Reinforcement":[13],"Learning.":[14],"While":[15],"most":[16],"existing":[17],"methods":[18,116],"utilize":[19],"soft":[20],"constraints":[21],"limit":[23],"cumulative":[24],"violations,":[25],"robotic":[26,101],"control":[27],"scenarios":[28],"demand":[29],"that":[30,111],"instantaneous":[31],"safety":[32,39,46,80,102],"costs":[33],"also":[34],"converge":[35],"rapidly":[36],"following":[37],"excursion.":[40],"Inspired":[41],"by":[42],"practical":[43,51],"stability":[44,52,81],"from":[45,63],"control,":[47],"we":[48],"formulate":[49],"cost":[50],"as":[53],"novel":[55],"constraint.":[56,76],"We":[57],"introduce":[58],"DQ-learning,":[59],"an":[60],"algorithm":[61],"derived":[62],"D-learning,":[64],"differential":[66],"predictive":[67],"learning":[68],"method":[69],"ensuring":[70],"system":[71],"stability,":[72],"satisfy":[74],"this":[75,91],"DQ-learning":[77,112],"merges":[78],"the":[79,85],"of":[82,88],"D-learning":[83],"with":[84],"reward":[86],"optimality":[87],"Q-learning,":[89],"incorporating":[90],"constraint":[92,119],"within":[93],"policy":[95],"optimization":[96],"framework.":[97],"Evaluations":[98],"on":[99],"multiple":[100],"benchmarks":[103],"and":[104,121],"sim-to-real":[106],"drone":[107],"target-catching":[108],"task":[109],"demonstrate":[110],"significantly":[113],"outperforms":[114],"baseline":[115],"both":[118],"satisfaction":[120],"sample":[122],"efficiency.":[123]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-04-07T00:00:00"}