{"id":"https://openalex.org/W4383066094","doi":"https://doi.org/10.1109/icra48891.2023.10160581","title":"Training Efficient Controllers via Analytic Policy Gradient","display_name":"Training Efficient Controllers via Analytic Policy Gradient","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383066094","doi":"https://doi.org/10.1109/icra48891.2023.10160581"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/bitstreams/de9f3992-dd13-4b1f-8f58-d7248f9f2c72/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030280318","display_name":"Nina Wiedemann","orcid":"https://orcid.org/0000-0002-8160-7634"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Nina Wiedemann","raw_affiliation_strings":["University of Zurich,Robotics and Perception Group,Switzerland","Robotics and Perception Group, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Robotics and Perception Group,Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009491839","display_name":"Valentin W\u00fcest","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["CH","FR"],"is_corresponding":false,"raw_author_name":"Valentin W\u00fcest","raw_affiliation_strings":["Ecole Polytechnique Fédérale de Lausanne (EPFL),Laboratory of Intelligent Systems"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Fédérale de Lausanne (EPFL),Laboratory of Intelligent Systems","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075873122","display_name":"Antonio Loquercio","orcid":"https://orcid.org/0000-0002-8410-3933"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Antonio Loquercio","raw_affiliation_strings":["University of Zurich,Robotics and Perception Group,Switzerland","Robotics and Perception Group, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Robotics and Perception Group,Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783024","display_name":"Matthias M\u00fcller","orcid":"https://orcid.org/0009-0003-0614-0733"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias M\u00fcller","raw_affiliation_strings":["Intel,Embodied AI Lab","Embodied AI Lab, Intel"],"affiliations":[{"raw_affiliation_string":"Intel,Embodied AI Lab","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Embodied AI Lab, Intel","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059369445","display_name":"Dario Floreano","orcid":"https://orcid.org/0000-0002-5330-4863"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH","FR"],"is_corresponding":false,"raw_author_name":"Dario Floreano","raw_affiliation_strings":["Ecole Polytechnique Fédérale de Lausanne (EPFL),Laboratory of Intelligent Systems"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique Fédérale de Lausanne (EPFL),Laboratory of Intelligent Systems","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057116316","display_name":"Davide Scaramuzza","orcid":"https://orcid.org/0000-0002-3831-6778"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Davide Scaramuzza","raw_affiliation_strings":["University of Zurich,Robotics and Perception Group,Switzerland","Robotics and Perception Group, University of Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Robotics and Perception Group,Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Robotics and Perception Group, University of Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030280318"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":2.0324,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86505881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1349","last_page":"1356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9943000078201294,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9902999997138977,"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/computer-science","display_name":"Computer science","score":0.7841861248016357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7510814666748047},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.679857611656189},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6600835919380188},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5731873512268066},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5470923781394958},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.5260142087936401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124383568763733},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.511078953742981},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.500622034072876},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.4886534512042999},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4824838936328888},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.47778162360191345},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3290737271308899},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2683839797973633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22560283541679382},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09962809085845947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841861248016357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7510814666748047},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.679857611656189},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6600835919380188},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5731873512268066},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5470923781394958},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.5260142087936401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124383568763733},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.511078953742981},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.500622034072876},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.4886534512042999},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4824838936328888},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.47778162360191345},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3290737271308899},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2683839797973633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22560283541679382},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09962809085845947},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10160581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:302950","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/198218","pdf_url":"https://infoscience.epfl.ch/bitstreams/de9f3992-dd13-4b1f-8f58-d7248f9f2c72/download","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:302950","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/198218","pdf_url":"https://infoscience.epfl.ch/bitstreams/de9f3992-dd13-4b1f-8f58-d7248f9f2c72/download","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4383066094.pdf"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1993488883","https://openalex.org/W2065569846","https://openalex.org/W2091565802","https://openalex.org/W2103581399","https://openalex.org/W2107878631","https://openalex.org/W2110139691","https://openalex.org/W2121863487","https://openalex.org/W2140135625","https://openalex.org/W2143770247","https://openalex.org/W2556096037","https://openalex.org/W2569321920","https://openalex.org/W2615395590","https://openalex.org/W2736601468","https://openalex.org/W2749680651","https://openalex.org/W2754000639","https://openalex.org/W2769498435","https://openalex.org/W2842089854","https://openalex.org/W2891122218","https://openalex.org/W2949571867","https://openalex.org/W2962822327","https://openalex.org/W2963280855","https://openalex.org/W2963755523","https://openalex.org/W2964006217","https://openalex.org/W2979489357","https://openalex.org/W2995253198","https://openalex.org/W2995298643","https://openalex.org/W3003038987","https://openalex.org/W3038570409","https://openalex.org/W3079027995","https://openalex.org/W3082697078","https://openalex.org/W3101071828","https://openalex.org/W3106018402","https://openalex.org/W3123524846","https://openalex.org/W3127216876","https://openalex.org/W3129381512","https://openalex.org/W3155729845","https://openalex.org/W3156330606","https://openalex.org/W3217056046","https://openalex.org/W4206742276","https://openalex.org/W4221153513","https://openalex.org/W4226325906","https://openalex.org/W4287113927","https://openalex.org/W4288601329","https://openalex.org/W4289294484","https://openalex.org/W4295312788","https://openalex.org/W4298206671","https://openalex.org/W4394649112","https://openalex.org/W6639949747","https://openalex.org/W6680657880","https://openalex.org/W6741002519","https://openalex.org/W6751494529","https://openalex.org/W6752307458","https://openalex.org/W6754133580","https://openalex.org/W6754471908","https://openalex.org/W6756256016","https://openalex.org/W6766978945","https://openalex.org/W6769017845","https://openalex.org/W6771217966","https://openalex.org/W6771699448","https://openalex.org/W6772521232","https://openalex.org/W6779443327","https://openalex.org/W6782364735","https://openalex.org/W6782486772","https://openalex.org/W6790411549","https://openalex.org/W6790633885","https://openalex.org/W6794067299","https://openalex.org/W6797154179","https://openalex.org/W6803702928","https://openalex.org/W6810192834","https://openalex.org/W6864195360"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W2101188133","https://openalex.org/W3202234113","https://openalex.org/W2388038580","https://openalex.org/W4385221652","https://openalex.org/W4246849984","https://openalex.org/W3214856188","https://openalex.org/W2967393875","https://openalex.org/W3085055827","https://openalex.org/W1974500578"],"abstract_inverted_index":{"Control":[0,24],"design":[1],"for":[2,199],"robotic":[3],"systems":[4,69],"is":[5,81,86],"complex":[6],"and":[7,51,131,141,148,158,211],"often":[8],"requires":[9],"solving":[10],"an":[11,77,90,178],"optimization":[12,19,42],"to":[13,29,96,172],"follow":[14],"a":[15,109,134,146,149,195],"trajectory":[16,65],"accurately.":[17],"Online":[18],"approaches":[20],"like":[21],"Model":[22],"Predictive":[23],"(MPC)":[25],"have":[26],"been":[27],"shown":[28],"achieve":[30],"great":[31],"tracking":[32,66,117,165],"performance,":[33],"but":[34,57],"require":[35],"high":[36],"computing":[37],"power.":[38],"Conversely,":[39],"learning-based":[40],"offline":[41,111],"approaches,":[43],"such":[44,73],"as":[45,74,194],"Reinforcement":[46],"Learning":[47],"(RL),":[48],"allow":[49],"fast":[50],"efficient":[52,82],"execution":[53,84],"on":[54,115,133],"the":[55,60,102,116,139,190,203],"robot":[56],"hardly":[58],"match":[59],"accuracy":[61],"of":[62,104,164,180,192,205],"MPC":[63,173],"in":[64,162],"tasks.":[67],"In":[68],"with":[70,112,126],"limited":[71],"compute,":[72],"aerial":[75,144],"vehicles,":[76],"accurate":[78],"controller":[79,110],"that":[80,123],"at":[83],"time":[85],"imperative.":[87],"We":[88,119],"propose":[89],"Analytic":[91],"Policy":[92],"Gradient":[93],"(APG)":[94],"method":[95,154,198],"tackle":[97],"this":[98],"problem.":[99],"APG":[100,127,193],"exploits":[101],"availability":[103],"differentiable":[105],"simulators":[106],"by":[107],"training":[108,121],"gradient":[113],"descent":[114],"error.":[118,166],"address":[120],"instabilities":[122],"frequently":[124],"occur":[125],"through":[128],"curriculum":[129],"learning":[130],"experiment":[132],"widely":[135],"used":[136],"controls":[137],"benchmark,":[138],"CartPole,":[140],"two":[142],"common":[143],"robots,":[145],"quadrotor":[147],"fixed-wing":[150],"drone.":[151],"Our":[152,185],"proposed":[153],"outperforms":[155],"both":[156],"model-based":[157],"model-free":[159],"RL":[160],"methods":[161],"terms":[163],"Concurrently,":[167],"it":[168,213],"achieves":[169],"similar":[170],"performance":[171],"while":[174],"requiring":[175],"more":[176],"than":[177],"order":[179],"magnitude":[181],"less":[182],"computation":[183],"time.":[184],"work":[186],"provides":[187],"insights":[188],"into":[189],"potential":[191],"promising":[196],"control":[197],"robotics.":[200],"To":[201],"facilitate":[202],"exploration":[204],"APG,":[206],"we":[207],"open-source":[208],"our":[209],"code":[210],"make":[212],"available":[214],"atgithub.com/lis-epfl/apg_trajectory_tracking.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}