{"id":"https://openalex.org/W3107340790","doi":null,"title":"Neural Network iLQR: A New Reinforcement Learning Architecture.","display_name":"Neural Network iLQR: A New Reinforcement Learning Architecture.","publication_year":2020,"publication_date":"2020-11-21","ids":{"openalex":"https://openalex.org/W3107340790","mag":"3107340790"},"language":"en","primary_location":{"id":"mag:3107340790","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.10737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2011.10737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054761774","display_name":"Zilong Cheng","orcid":"https://orcid.org/0000-0003-3195-1258","observed_orcids":["https://orcid.org/0000-0003-3195-1258"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zilong Cheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3195-1258","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053340150","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-9405-8232","observed_orcids":["https://orcid.org/0000-0002-9405-8232"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9405-8232","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704348","display_name":"Xiaoxue Zhang","orcid":"https://orcid.org/0000-0002-8910-8477","observed_orcids":["https://orcid.org/0000-0002-8910-8477"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxue Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8910-8477","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615","observed_orcids":["https://orcid.org/0000-0003-4074-1615"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026685411","display_name":"Tong Heng Lee","orcid":"https://orcid.org/0000-0002-2785-516X","observed_orcids":["https://orcid.org/0000-0002-2785-516X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Heng Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5922999978065491,"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":0.5922999978065491,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.4036000072956085,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/iterative-linear-quadratic-regulator","display_name":"iterative linear quadratic regulator","score":0.9570000171661377},{"id":"https://openalex.org/keywords/model-free-optimal-control","display_name":"model-free optimal control","score":0.7200000286102295},{"id":"https://openalex.org/keywords/exploration-in-reinforcement-learning","display_name":"exploration in reinforcement learning","score":0.6389999985694885},{"id":"https://openalex.org/keywords/unknown-system-model","display_name":"unknown system model","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8681405782699585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465746164321899},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6421298980712891},{"id":"https://openalex.org/C2777705401","wikidata":"https://www.wikidata.org/wiki/Q6457570","display_name":"LEAPS","level":2,"score":0.607057511806488},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.6019829511642456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633171796798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44431164860725403},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44103533029556274},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3107340790","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.10737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3107340790","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.10737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1778554682","https://openalex.org/W1964946446","https://openalex.org/W1980035368","https://openalex.org/W2073677587","https://openalex.org/W2087617385","https://openalex.org/W2104733512","https://openalex.org/W2130913800","https://openalex.org/W2156737235","https://openalex.org/W2168501056","https://openalex.org/W2215032184","https://openalex.org/W2260756217","https://openalex.org/W2419438630","https://openalex.org/W2529658650","https://openalex.org/W2623431351","https://openalex.org/W2762329249","https://openalex.org/W2772589676","https://openalex.org/W2788862220","https://openalex.org/W2798520605","https://openalex.org/W2803933017","https://openalex.org/W2823112946","https://openalex.org/W2883972132","https://openalex.org/W2892230114","https://openalex.org/W2898585845","https://openalex.org/W2904455790","https://openalex.org/W2924607344","https://openalex.org/W2963673305","https://openalex.org/W2963704132","https://openalex.org/W2970283989","https://openalex.org/W2973127235","https://openalex.org/W2981237928","https://openalex.org/W3005988330","https://openalex.org/W3006640981","https://openalex.org/W3020377178","https://openalex.org/W3046182053","https://openalex.org/W3088521775","https://openalex.org/W3098391110","https://openalex.org/W4287617987"],"related_works":["https://openalex.org/W4388843255","https://openalex.org/W4405724815","https://openalex.org/W2032252420","https://openalex.org/W4390099565","https://openalex.org/W3150415100","https://openalex.org/W3114329882","https://openalex.org/W7067289523","https://openalex.org/W2887843158","https://openalex.org/W4210704481","https://openalex.org/W7134036450"],"abstract_inverted_index":{"As":[0,155],"a":[1,54,81,97],"notable":[2],"machine":[3],"learning":[4,14,25,37,57],"paradigm,":[5],"the":[6,10,28,32,35,41,64,71,103,106,110,119,129,140,146,153,159,170],"research":[7],"efforts":[8],"in":[9,137,152,162],"context":[11],"of":[12,34,66,70,80,105,112,118,139,145,149,169],"reinforcement":[13,24,36,56],"have":[15],"certainly":[16],"progressed":[17],"leaps":[18],"and":[19,49,61],"bounds.":[20],"When":[21],"compared":[22],"with":[23,27],"methods":[26],"given":[29,141],"system":[30,72,113],"model,":[31,73],"methodology":[33],"architecture":[38,58],"based":[39],"on":[40,91],"unknown":[42],"model":[43],"generally":[44],"exhibits":[45],"significantly":[46,127],"broader":[47],"universality":[48],"applicability.":[50],"In":[51],"this":[52,94,125],"work,":[53],"new":[55,99],"is":[59,75],"developed":[60],"presented":[62],"without":[63],"requirement":[65],"any":[67],"prior":[68],"knowledge":[69],"which":[74],"termed":[76],"as":[77],"an":[78],"approach":[79,126],"neural":[120],"network":[83,121],"iterative":[84,116,131],"linear":[85,132],"quadratic":[86,133],"regulator":[87,134],"(NNiLQR).":[88],"Depending":[89],"solely":[90],"measurement":[92],"data,":[93],"method":[95,136,172],"yields":[96],"completely":[98],"non-parametric":[100],"routine":[101],"for":[102],"establishment":[104],"optimal":[107],"policy":[108],"(without":[109],"necessity":[111],"modeling)":[114],"through":[115],"refinements":[117],"system.":[122],"Rather":[123],"importantly,":[124],"outperforms":[128],"classical":[130],"(iLQR)":[135],"terms":[138],"objective":[142],"function":[143],"because":[144],"innovative":[147],"utilization":[148],"further":[150],"exploration":[151],"methodology.":[154],"clearly":[156],"indicated":[157],"from":[158],"results":[160],"attained":[161],"two":[163],"illustrative":[164],"examples,":[165],"these":[166],"significant":[167],"merits":[168],"NNiLQR":[171],"are":[173],"demonstrated":[174],"rather":[175],"evidently.":[176]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-12-07T00:00:00"}