{"id":"https://openalex.org/W4365790399","doi":"https://doi.org/10.1109/lra.2023.3266985","title":"CACTO: Continuous Actor-Critic With Trajectory Optimization\u2014Towards Global Optimality","display_name":"CACTO: Continuous Actor-Critic With Trajectory Optimization\u2014Towards Global Optimality","publication_year":2023,"publication_date":"2023-04-13","ids":{"openalex":"https://openalex.org/W4365790399","doi":"https://doi.org/10.1109/lra.2023.3266985"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3266985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3266985","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://iris.unitn.it/bitstream/11572/376907/1/CACTO.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001888749","display_name":"Gianluigi Grandesso","orcid":"https://orcid.org/0000-0002-3016-2751"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluigi Grandesso","raw_affiliation_strings":["Department of Industrial Engineering, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3016-2751","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079139044","display_name":"Elisa Alboni","orcid":"https://orcid.org/0000-0002-5672-453X"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Alboni","raw_affiliation_strings":["Department of Industrial Engineering, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5672-453X","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063378213","display_name":"Gastone Pietro Rosati Papini","orcid":"https://orcid.org/0000-0003-1075-9603"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gastone P. Rosati Papini","raw_affiliation_strings":["Department of Industrial Engineering, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1075-9603","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029126529","display_name":"Patrick M. Wensing","orcid":"https://orcid.org/0000-0002-9041-5175"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick M. Wensing","raw_affiliation_strings":["Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-9041-5175","affiliations":[{"raw_affiliation_string":"Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038165484","display_name":"Andrea Del Prete","orcid":"https://orcid.org/0000-0003-1275-2851"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Del Prete","raw_affiliation_strings":["Department of Industrial Engineering, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1275-2851","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":2.7099,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9173889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"8","issue":"6","first_page":"3318","last_page":"3325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.7922638654708862},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6601946353912354},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.6398061513900757},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6292505264282227},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6198315620422363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5743241310119629},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5433242917060852},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.541715681552887},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5000977516174316},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.46607089042663574},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45392319560050964},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4537303149700165},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.44157472252845764},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.43269604444503784},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4123360514640808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.294281542301178},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23331546783447266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21362268924713135},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.12329813838005066},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.10311740636825562}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.7922638654708862},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6601946353912354},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.6398061513900757},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6292505264282227},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6198315620422363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5743241310119629},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5433242917060852},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.541715681552887},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5000977516174316},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.46607089042663574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45392319560050964},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4537303149700165},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.44157472252845764},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.43269604444503784},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4123360514640808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.294281542301178},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23331546783447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21362268924713135},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.12329813838005066},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.10311740636825562},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/lra.2023.3266985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3266985","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/376907","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/376907","pdf_url":"https://iris.unitn.it/bitstream/11572/376907/1/CACTO.pdf","source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.unitn.it:11572/376907","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/376907","pdf_url":"https://iris.unitn.it/bitstream/11572/376907/1/CACTO.pdf","source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317295","display_name":"Dipartimenti di Eccellenza","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4365790399.pdf","grobid_xml":"https://content.openalex.org/works/W4365790399.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1487586009","https://openalex.org/W1515641485","https://openalex.org/W1522301498","https://openalex.org/W2003132288","https://openalex.org/W2037490650","https://openalex.org/W2123871098","https://openalex.org/W2132202988","https://openalex.org/W2295431040","https://openalex.org/W2313274380","https://openalex.org/W2561843528","https://openalex.org/W2565077851","https://openalex.org/W2577634205","https://openalex.org/W2741122588","https://openalex.org/W2747402019","https://openalex.org/W2771691050","https://openalex.org/W2904246096","https://openalex.org/W2911477000","https://openalex.org/W2922301133","https://openalex.org/W2968213087","https://openalex.org/W2973229164","https://openalex.org/W2998069546","https://openalex.org/W3081791272","https://openalex.org/W3101144081","https://openalex.org/W3104730803","https://openalex.org/W3118951974","https://openalex.org/W3144743376","https://openalex.org/W3156116643","https://openalex.org/W3156261936","https://openalex.org/W4214717370","https://openalex.org/W4300309110","https://openalex.org/W6631190155","https://openalex.org/W6675999342","https://openalex.org/W6696324988","https://openalex.org/W6739475399","https://openalex.org/W6742461812","https://openalex.org/W6742945991","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6757592117","https://openalex.org/W6791374197"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W2354676191","https://openalex.org/W3188646203","https://openalex.org/W136674370","https://openalex.org/W2909957174","https://openalex.org/W2105527480","https://openalex.org/W4320035781","https://openalex.org/W2052387497","https://openalex.org/W2015961810","https://openalex.org/W2154722715"],"abstract_inverted_index":{"This":[0],"letter":[1],"presents":[2],"a":[3,23,48,69,103,151,158],"novel":[4],"algorithm":[5,30,101],"for":[6,119],"the":[7,32,62,73,84,96,122,165,180],"continuous":[8,43,79],"control":[9,82,105],"of":[10,36,168],"dynamical":[11,148],"systems":[12,45],"that":[13],"combines":[14],"Trajectory":[15],"Optimization":[16,189],"(TO)":[17],"and":[18,38,81,92,157,186],"Reinforcement":[19],"Learning":[20],"(RL)":[21],"in":[22,57,170],"single":[24],"framework.":[25],"The":[26],"motivations":[27],"behind":[28],"this":[29],"are":[31],"two":[33],"main":[34],"limitations":[35],"TO":[37,53],"RL":[39,85,109,191],"when":[40,61,76,113],"applied":[41],"to":[42,46,68,128,130],"nonlinear":[44],"minimize":[47],"non-convex":[49,143],"cost":[50],"function.":[51],"Specifically,":[52],"can":[54],"get":[55],"stuck":[56],"poor":[58,131],"local":[59,132,172],"minima":[60],"search":[63,111],"is":[64,136],"not":[65],"initialized":[66],"close":[67],"\u201cgood\u201d":[70,104],"minimum.":[71],"On":[72],"other":[74],"hand,":[75],"dealing":[77],"with":[78,146,154],"state":[80],"spaces,":[83],"training":[86],"process":[87,125],"may":[88],"be":[89],"excessively":[90],"long":[91],"strongly":[93],"dependent":[94],"on":[95,138],"exploration":[97],"strategy.":[98],"Thus,":[99],"our":[100],"learns":[102],"policy":[106,110],"via":[107],"TO-guided":[108],"that,":[112],"used":[114],"as":[115],"initial":[116],"guess":[117],"provider":[118],"TO,":[120],"makes":[121],"trajectory":[123],"optimization":[124],"less":[126],"prone":[127],"converge":[129],"optima.":[133],"Our":[134,162],"method":[135],"validated":[137],"several":[139],"reaching":[140],"problems":[141],"featuring":[142],"obstacle":[144],"avoidance":[145],"different":[147],"systems,":[149],"including":[150],"car":[152],"model":[153],"6D":[155],"state,":[156],"3-joint":[159],"planar":[160],"manipulator.":[161],"results":[163],"show":[164],"great":[166],"capabilities":[167],"CACTO":[169],"escaping":[171],"minima,":[173],"while":[174],"being":[175],"more":[176],"computationally":[177],"efficient":[178],"than":[179],"Deep":[181],"Deterministic":[182],"Policy":[183,188],"Gradient":[184],"(DDPG)":[185],"Proximal":[187],"(PPO)":[190],"algorithms.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}