{"id":"https://openalex.org/W4317383008","doi":"https://doi.org/10.1109/robio55434.2022.10011977","title":"Learning to Solve Nonlinear Optimization Problem with Deep Reinforcement Learning","display_name":"Learning to Solve Nonlinear Optimization Problem with Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383008","doi":"https://doi.org/10.1109/robio55434.2022.10011977"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011977","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011977","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-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/A5001956754","display_name":"Yue Gao","orcid":"https://orcid.org/0000-0002-8901-9335"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Gao","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence and AI Institute,Shanghai,P.R. China","MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University, Shanghai, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence and AI Institute,Shanghai,P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100848448","display_name":"Qiyue Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyue Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China","Department of Automation, Shanghai Jiao Tong University, Shanghai, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072912465","display_name":"Huajian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huajian Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China","Department of Automation, Shanghai Jiao Tong University, Shanghai, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101771487","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0003-2977-6892"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China","Department of Automation, Shanghai Jiao Tong University, Shanghai, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.3507,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53320588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"518","issue":null,"first_page":"909","last_page":"914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9997000098228455,"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/T11236","display_name":"Control Systems and Identification","score":0.9927999973297119,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926999807357788,"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/nonlinear-system","display_name":"Nonlinear system","score":0.5920178890228271},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5711642503738403},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5504891276359558},{"id":"https://openalex.org/keywords/non-linear-least-squares","display_name":"Non-linear least squares","score":0.5330499410629272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4958682954311371},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.48161667585372925},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4809347987174988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46609747409820557},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45604801177978516},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4381873607635498},{"id":"https://openalex.org/keywords/newtons-method","display_name":"Newton's method","score":0.43706148862838745},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.432742178440094},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.4313086271286011},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3399220108985901},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33169010281562805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2555711269378662},{"id":"https://openalex.org/keywords/explained-sum-of-squares","display_name":"Explained sum of squares","score":0.17725679278373718}],"concepts":[{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5920178890228271},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5711642503738403},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5504891276359558},{"id":"https://openalex.org/C45923927","wikidata":"https://www.wikidata.org/wiki/Q3319230","display_name":"Non-linear least squares","level":3,"score":0.5330499410629272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4958682954311371},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.48161667585372925},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4809347987174988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46609747409820557},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45604801177978516},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4381873607635498},{"id":"https://openalex.org/C85189116","wikidata":"https://www.wikidata.org/wiki/Q374195","display_name":"Newton's method","level":3,"score":0.43706148862838745},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.432742178440094},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.4313086271286011},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3399220108985901},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33169010281562805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2555711269378662},{"id":"https://openalex.org/C49847556","wikidata":"https://www.wikidata.org/wiki/Q3964631","display_name":"Explained sum of squares","level":2,"score":0.17725679278373718},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011977","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011977","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W147998453","https://openalex.org/W1966523582","https://openalex.org/W1997138910","https://openalex.org/W2073787051","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2159307101","https://openalex.org/W2256578114","https://openalex.org/W2786092665","https://openalex.org/W2895289727","https://openalex.org/W2897250035","https://openalex.org/W2897830584","https://openalex.org/W2952436057","https://openalex.org/W2963864421","https://openalex.org/W6683195989","https://openalex.org/W6684921986","https://openalex.org/W6764398373"],"related_works":["https://openalex.org/W2026673180","https://openalex.org/W1959514624","https://openalex.org/W200101083","https://openalex.org/W2939592218","https://openalex.org/W2359835307","https://openalex.org/W327962130","https://openalex.org/W4380487384","https://openalex.org/W1997338499","https://openalex.org/W4378552425","https://openalex.org/W2589353378"],"abstract_inverted_index":{"Nonlinear":[0],"least-squares":[1,52],"problems":[2,89],"(NLS)":[3],"are":[4],"pop-ular":[5],"in":[6,68,96],"engineering":[7],"and":[8,18,29,75,93,102],"scientific":[9],"fields.":[10],"Traditional":[11],"optimization":[12,42],"methods":[13],"such":[14],"as":[15],"Newton's":[16,66],"method":[17,20,43,64,67],"Gaussian-Newton":[19],"(GN)":[21],"suffer":[22],"from":[23],"the":[24,30,62],"sensibility":[25],"to":[26,49],"initial":[27,76],"values":[28,77],"high":[31],"computational":[32],"complexity.":[33],"In":[34,79],"this":[35],"paper,":[36],"we":[37],"propose":[38],"LS-DDPG,":[39],"a":[40],"robust":[41],"utilizing":[44],"deep":[45],"rein-forcement":[46],"learning":[47],"algorithms":[48],"solve":[50],"nonlinear":[51],"problems.":[53],"The":[54],"experiment":[55],"results":[56],"on":[57,84],"synthetic":[58],"data":[59],"demonstrate":[60],"that":[61],"proposed":[63],"outperforms":[65],"terms":[69],"of":[70],"computation":[71],"cost,":[72],"convergence":[73],"speed":[74],"sensibility.":[78],"addition,":[80],"LS-DDPG":[81],"is":[82],"utilized":[83],"model":[85],"predictive":[86],"control":[87],"(MPC)":[88],"for":[90],"trajectory":[91],"planning":[92],"tracking":[94],"tasks":[95],"self-driving":[97],"with":[98],"longer":[99],"prediction":[100],"horizon":[101],"higher":[103],"accuracy":[104],"than":[105],"baseline":[106],"methods.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}