{"id":"https://openalex.org/W4412431758","doi":"https://doi.org/10.1109/med64031.2025.11073478","title":"Accelerating Model-Based Reinforcement Learning using Non-Linear Trajectory Optimization","display_name":"Accelerating Model-Based Reinforcement Learning using Non-Linear Trajectory Optimization","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4412431758","doi":"https://doi.org/10.1109/med64031.2025.11073478"},"language":"en","primary_location":{"id":"doi:10.1109/med64031.2025.11073478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/med64031.2025.11073478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 33rd Mediterranean Conference on Control and Automation (MED)","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/A5103719063","display_name":"Marco Cal\u00ed","orcid":"https://orcid.org/0009-0002-4977-822X"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Marco Cali\u2019","raw_affiliation_strings":["University of Padua,Department of Information Engineering,Padua,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padua,Department of Information Engineering,Padua,Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039774985","display_name":"Giulio Giacomuzzo","orcid":"https://orcid.org/0009-0002-1172-5712"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Giacomuzzo","raw_affiliation_strings":["University of Padua,Department of Information Engineering,Padua,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padua,Department of Information Engineering,Padua,Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089846134","display_name":"Ruggero Carli","orcid":"https://orcid.org/0000-0002-6506-5898"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ruggero Carli","raw_affiliation_strings":["University of Padua,Department of Information Engineering,Padua,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padua,Department of Information Engineering,Padua,Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040482614","display_name":"Alberto Dalla Libera","orcid":"https://orcid.org/0000-0002-7656-7797"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Dalla Libera","raw_affiliation_strings":["University of Padua,Department of Information Engineering,Padua,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padua,Department of Information Engineering,Padua,Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103719063"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08133753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"460","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9988999962806702,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8078479170799255},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7091467976570129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901115775108337},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.48786306381225586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3788207769393921},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3409807085990906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1238957941532135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8078479170799255},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7091467976570129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901115775108337},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.48786306381225586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3788207769393921},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3409807085990906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1238957941532135},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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":2,"locations":[{"id":"doi:10.1109/med64031.2025.11073478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/med64031.2025.11073478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 33rd Mediterranean Conference on Control and Automation (MED)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research.unipd.it:11577/3562782","is_oa":false,"landing_page_url":"https://hdl.handle.net/11577/3562782","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W1587009522","https://openalex.org/W1964946446","https://openalex.org/W2046633936","https://openalex.org/W2560674852","https://openalex.org/W2580909119","https://openalex.org/W2604883922","https://openalex.org/W4211049957","https://openalex.org/W4382935723","https://openalex.org/W4401025088","https://openalex.org/W6680657880","https://openalex.org/W6692170166","https://openalex.org/W6751907673","https://openalex.org/W6789151446"],"related_works":["https://openalex.org/W4385832323","https://openalex.org/W4244391535","https://openalex.org/W2356996864","https://openalex.org/W2904060783","https://openalex.org/W2015393961","https://openalex.org/W2378339670","https://openalex.org/W2359353485","https://openalex.org/W2361427670","https://openalex.org/W2139910871","https://openalex.org/W2119925415"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,57,61,69,93,109],"slow":[4],"policy":[5],"optimization":[6,36,65],"convergence":[7,76],"of":[8,63],"Monte":[9],"Carlo":[10],"Probabilistic":[11],"Inference":[12],"for":[13,39],"Learning":[14],"Control":[15],"(MC-PILCO),":[16],"a":[17,33,101],"state-of-the-art":[18],"model-based":[19],"reinforcement":[20],"learning":[21],"(MBRL)":[22],"algorithm,":[23],"by":[24],"integrating":[25],"it":[26],"with":[27],"iterative":[28],"Linear":[29],"Quadratic":[30],"Regulator":[31],"(iLQR),":[32],"fast":[34],"trajectory":[35],"method":[37],"suitable":[38],"nonlinear":[40],"systems.":[41],"The":[42],"proposed":[43],"method,":[44],"Exploration-Boosted":[45],"MC-PILCO":[46,116],"(EB-MC-PILCO),":[47],"leverages":[48],"iLQR":[49],"to":[50,78,83],"generate":[51],"informative,":[52],"exploratory":[53],"trajectories":[54],"and":[55],"initialize":[56],"policy,":[58],"significantly":[59],"reducing":[60],"number":[62],"required":[64],"steps.":[66],"Experiments":[67],"on":[68],"cart-pole":[70],"task":[71,94,110],"demonstrate":[72],"that":[73],"EB-MC-PILCO":[74,98],"accelerates":[75],"compared":[77],"standard":[79],"MC-PILCO,":[80],"achieving":[81],"up":[82],"45.9%":[84],"reduction":[85],"in":[86,95,113,118],"execution":[87],"time":[88],"when":[89],"both":[90],"methods":[91],"solve":[92],"four":[96],"trials.":[97],"also":[99],"maintains":[100],"100%":[102],"success":[103],"rate":[104],"across":[105],"trials":[106],"while":[107],"solving":[108],"faster,":[111],"even":[112],"cases":[114],"where":[115],"converges":[117],"fewer":[119],"iterations.":[120]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}