{"id":"https://openalex.org/W3092240274","doi":"https://doi.org/10.1109/cdc42340.2020.9303931","title":"Learning Dynamic-Objective Policies from a Class of Optimal Trajectories","display_name":"Learning Dynamic-Objective Policies from a Class of Optimal Trajectories","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3092240274","doi":"https://doi.org/10.1109/cdc42340.2020.9303931","mag":"3092240274"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9303931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.10139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019272905","display_name":"Christopher Iliffe Sprague","orcid":"https://orcid.org/0000-0003-4943-2501"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Christopher Iliffe Sprague","raw_affiliation_strings":["Robotics, Perception and Learning Lab., Royal Institute of Technology (KTH), Stockholm, Sweden","Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Robotics, Perception and Learning Lab., Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020258120","display_name":"Dario Izzo","orcid":"https://orcid.org/0000-0002-9846-8423"},"institutions":[{"id":"https://openalex.org/I2801994115","display_name":"European Space Agency","ror":"https://ror.org/03wd9za21","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2801994115"]},{"id":"https://openalex.org/I44377176","display_name":"European Space Research and Technology Centre","ror":"https://ror.org/03h3jqn23","country_code":"NL","type":"government","lineage":["https://openalex.org/I2801994115","https://openalex.org/I44377176"]}],"countries":["FR","NL"],"is_corresponding":false,"raw_author_name":"Dario Izzo","raw_affiliation_strings":["Advanced Concepts Team, European Space Technology Center (ESTEC), Noordwijk, The Netherlands","European Space Agency"],"affiliations":[{"raw_affiliation_string":"Advanced Concepts Team, European Space Technology Center (ESTEC), Noordwijk, The Netherlands","institution_ids":["https://openalex.org/I44377176"]},{"raw_affiliation_string":"European Space Agency","institution_ids":["https://openalex.org/I2801994115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070754732","display_name":"Petter \u00d6gren","orcid":"https://orcid.org/0000-0002-7714-928X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Petter Ogren","raw_affiliation_strings":["Robotics, Perception and Learning Lab., Royal Institute of Technology (KTH), Stockholm, Sweden","Royal Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Robotics, Perception and Learning Lab., Royal Institute of Technology (KTH), Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019272905"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12712929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"597","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991100013256073,"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":0.991100013256073,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.921999990940094,"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/trajectory","display_name":"Trajectory","score":0.7269704937934875},{"id":"https://openalex.org/keywords/continuation","display_name":"Continuation","score":0.7150075435638428},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.6367709636688232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6092392802238464},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5979181528091431},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5401185750961304},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5120211243629456},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5104071497917175},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5037609934806824},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5004558563232422},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.49727752804756165},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.47811001539230347},{"id":"https://openalex.org/keywords/numerical-continuation","display_name":"Numerical continuation","score":0.4378732740879059},{"id":"https://openalex.org/keywords/homotopy","display_name":"Homotopy","score":0.4293982982635498},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42221033573150635},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2930574417114258},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.23454737663269043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17312216758728027},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10982093214988708},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.10333830118179321}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7269704937934875},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.7150075435638428},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.6367709636688232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6092392802238464},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5979181528091431},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5401185750961304},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5120211243629456},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5104071497917175},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5037609934806824},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5004558563232422},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.49727752804756165},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.47811001539230347},{"id":"https://openalex.org/C2775978667","wikidata":"https://www.wikidata.org/wiki/Q7069654","display_name":"Numerical continuation","level":4,"score":0.4378732740879059},{"id":"https://openalex.org/C5961521","wikidata":"https://www.wikidata.org/wiki/Q746083","display_name":"Homotopy","level":2,"score":0.4293982982635498},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42221033573150635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2930574417114258},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23454737663269043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17312216758728027},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10982093214988708},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.10333830118179321},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2781349735","wikidata":"https://www.wikidata.org/wiki/Q4904824","display_name":"Bifurcation","level":3,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc42340.2020.9303931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.10139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.10139","pdf_url":"https://arxiv.org/pdf/1902.10139","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:3092240274","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1902.10139","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.1902.10139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.10139","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.10139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.10139","pdf_url":"https://arxiv.org/pdf/1902.10139","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092240274.pdf","grobid_xml":"https://content.openalex.org/works/W3092240274.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1570420806","https://openalex.org/W1987725948","https://openalex.org/W1998649829","https://openalex.org/W2023934148","https://openalex.org/W2028678875","https://openalex.org/W2087884651","https://openalex.org/W2104694979","https://openalex.org/W2116773335","https://openalex.org/W2121863487","https://openalex.org/W2144144709","https://openalex.org/W2173248099","https://openalex.org/W2221321873","https://openalex.org/W2225069804","https://openalex.org/W2546070262","https://openalex.org/W2567444783","https://openalex.org/W2736601468","https://openalex.org/W2771691050","https://openalex.org/W2774922731","https://openalex.org/W2787725528","https://openalex.org/W2804930149","https://openalex.org/W2892165885","https://openalex.org/W2893725421","https://openalex.org/W2909686384","https://openalex.org/W2910124058","https://openalex.org/W2918149778","https://openalex.org/W2962804513","https://openalex.org/W2963594110","https://openalex.org/W2963641140","https://openalex.org/W2963646405","https://openalex.org/W2971638107","https://openalex.org/W4211147054","https://openalex.org/W6631190155","https://openalex.org/W6647175844","https://openalex.org/W6677916085","https://openalex.org/W6684921986","https://openalex.org/W6704571135","https://openalex.org/W6741002519","https://openalex.org/W6748318106","https://openalex.org/W6752165109","https://openalex.org/W6754554871","https://openalex.org/W6754964327"],"related_works":["https://openalex.org/W3119289712","https://openalex.org/W3091489580","https://openalex.org/W32048965","https://openalex.org/W2183483151","https://openalex.org/W3046540105","https://openalex.org/W3006506827","https://openalex.org/W163289901","https://openalex.org/W815900967","https://openalex.org/W3111862348","https://openalex.org/W2057972041","https://openalex.org/W311349729","https://openalex.org/W1565435882","https://openalex.org/W2790745335","https://openalex.org/W2796922012","https://openalex.org/W3104512559","https://openalex.org/W2541717968","https://openalex.org/W2511289655","https://openalex.org/W2947132895","https://openalex.org/W2914264703"],"abstract_inverted_index":{"Optimal":[0],"state-feedback":[1],"controllers,":[2,23,96],"capable":[3],"of":[4,50,85,92,144,153],"changing":[5],"between":[6],"different":[7],"objective":[8,103],"functions,":[9],"are":[10,137],"advantageous":[11],"to":[12,43,62,76,88,101,150],"systems":[13],"in":[14,132,155],"which":[15,97],"unexpected":[16],"situations":[17],"may":[18],"arise.":[19],"However,":[20],"synthesising":[21,44],"such":[22],"even":[24],"for":[25],"a":[26,30,38,48,120],"single":[27],"objective,":[28],"is":[29],"demanding":[31],"process.":[32],"In":[33],"this":[34,108],"paper,":[35],"we":[36,81],"present":[37],"novel":[39],"and":[40,55,70,73,119,124,147],"straightforward":[41],"approach":[42,109],"these":[45,75],"policies":[46,87],"through":[47],"combination":[49],"trajectory":[51,112,145],"optimisation,":[52],"homotopy":[53,148],"continuation,":[54],"imitation":[56],"learning.":[57],"We":[58,106],"use":[59,74],"numerical":[60],"continuation":[61,149],"efficiently":[63],"generate":[64],"optimal":[65,93],"demonstrations":[66],"across":[67,110],"several":[68],"objectives":[69],"boundary":[71],"conditions,":[72],"train":[77],"our":[78,86],"policies.":[79],"Additionally,":[80],"demonstrate":[82],"the":[83,127,142,151],"ability":[84],"effectively":[89],"learn":[90],"families":[91],"state-":[94],"feedback":[95],"can":[98],"be":[99],"used":[100],"change":[102],"functions":[104],"online.":[105],"illustrate":[107],"two":[111],"optimisation":[113,146],"problems,":[114],"an":[115],"inverted":[116],"pendulum":[117],"swingup":[118],"spacecraft":[121],"orbit":[122],"transfer,":[123],"show":[125],"that":[126,136],"synthesised":[128],"policies,":[129],"when":[130],"evaluated":[131],"simulation,":[133],"produce":[134],"trajectories":[135],"near-optimal.":[138],"These":[139],"results":[140],"indicate":[141],"benefit":[143],"synthesis":[152],"controllers":[154],"dynamic-objective":[156],"contexts.":[157]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}