{"id":"https://openalex.org/W4396753551","doi":"https://doi.org/10.1109/lra.2024.3398402","title":"Optimistic Reinforcement Learning-Based Skill Insertions for Task and Motion Planning","display_name":"Optimistic Reinforcement Learning-Based Skill Insertions for Task and Motion Planning","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396753551","doi":"https://doi.org/10.1109/lra.2024.3398402"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3398402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3398402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.14065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026703570","display_name":"Gaoyuan Liu","orcid":"https://orcid.org/0000-0002-9063-2751"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Gaoyuan Liu","raw_affiliation_strings":["Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"imec, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091185289","display_name":"Joris De Winter","orcid":"https://orcid.org/0000-0002-5818-7539"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Joris de Winter","raw_affiliation_strings":["Brubotics, Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093600424","display_name":"Yuri Durodi\u00e9","orcid":"https://orcid.org/0000-0002-9931-7037"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yuri Durodi\u00e9","raw_affiliation_strings":["Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"imec, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067283098","display_name":"Denis Steckelmacher","orcid":"https://orcid.org/0000-0003-1521-8494"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Denis Steckelmacher","raw_affiliation_strings":["Artificial Intelligence (AI) Lab, Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence (AI) Lab, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Nowe","raw_affiliation_strings":["Artificial Intelligence (AI) Lab, Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence (AI) Lab, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010914606","display_name":"Bram Vanderborght","orcid":"https://orcid.org/0000-0003-4881-9341"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bram Vanderborght","raw_affiliation_strings":["Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Brubotics, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"imec, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026703570"],"corresponding_institution_ids":["https://openalex.org/I13469542","https://openalex.org/I4210114974"],"apc_list":null,"apc_paid":null,"fwci":0.3252,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52733865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":"6","first_page":"5974","last_page":"5981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9986000061035156,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8407463431358337},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7602920532226562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6983376741409302},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.66917884349823},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.650791347026825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5902730226516724},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5348867774009705},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5163282752037048},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.49606356024742126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44540515542030334},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.41829192638397217},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.29955601692199707},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.17343854904174805},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.15081903338432312},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13313069939613342},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12582266330718994}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8407463431358337},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7602920532226562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983376741409302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.66917884349823},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.650791347026825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5902730226516724},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5348867774009705},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5163282752037048},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.49606356024742126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44540515542030334},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.41829192638397217},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29955601692199707},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.17343854904174805},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.15081903338432312},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13313069939613342},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12582266330718994},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/lra.2024.3398402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3398402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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:arXiv.org:2510.14065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.14065","pdf_url":"https://arxiv.org/pdf/2510.14065","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:174583","is_oa":true,"landing_page_url":"https://biblio.vub.ac.be/vubir/optimistic-reinforcement-learningbased-skill-insertions-for-task-and-motion-planning(a6af9764-cad3-4919-8a85-e41bbd0bf0f3).html","pdf_url":"https://biblio.vub.ac.be/vubirfiles/117694641/ORL_TAMP_RAL_preprint.pdf","source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"publishedVersion"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:230074","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.14065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.14065","pdf_url":"https://arxiv.org/pdf/2510.14065","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1462399522","display_name":null,"funder_award_id":"101070596","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1475741780","https://openalex.org/W2041753526","https://openalex.org/W2070683816","https://openalex.org/W2109910161","https://openalex.org/W2135639338","https://openalex.org/W2412154694","https://openalex.org/W2735300570","https://openalex.org/W2786893837","https://openalex.org/W2805883505","https://openalex.org/W2811124360","https://openalex.org/W2962736495","https://openalex.org/W2963709735","https://openalex.org/W2984756091","https://openalex.org/W3001865277","https://openalex.org/W3003997138","https://openalex.org/W3004011906","https://openalex.org/W3039141704","https://openalex.org/W3089355520","https://openalex.org/W3098029877","https://openalex.org/W3098499184","https://openalex.org/W3103940950","https://openalex.org/W3150384095","https://openalex.org/W3176770340","https://openalex.org/W3189699967","https://openalex.org/W3201608505","https://openalex.org/W3215761265","https://openalex.org/W4205130889","https://openalex.org/W4360897660","https://openalex.org/W6713184877","https://openalex.org/W6755421158","https://openalex.org/W6764537672","https://openalex.org/W6838586813","https://openalex.org/W6858236821"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Task":[0],"and":[1,14,123,126,152],"motion":[2],"planning":[3,29,119,155],"(TAMP)":[4],"for":[5,39],"robotics":[6],"manipulation":[7,53],"necessitates":[8],"long-horizon":[9],"reasoning":[10],"involving":[11],"versatile":[12],"actions":[13,18,30],"skills.":[15],"While":[16],"deterministic":[17],"can":[19],"be":[20,91],"crafted":[21],"by":[22,93,137],"sampling":[23],"or":[24],"optimizing":[25],"with":[26,31,58,82,116,149],"certain":[27],"constraints,":[28],"uncertainty,":[32],"i.e.,":[33],"probabilistic":[34,150],"actions,":[35],"remains":[36],"a":[37,65,77],"challenge":[38],"TAMP.":[40],"On":[41],"the":[42,75,88,105,110,128,131,143,154,159],"contrary,":[43],"Reinforcement":[44],"Learning":[45],"(RL)":[46],"excels":[47],"in":[48],"acquiring":[49],"versatile,":[50],"yet":[51],"short-horizon,":[52],"skills":[54,70],"that":[55,67,86,136],"are":[56],"robust":[57],"uncertainties.":[59,108],"In":[60,109],"this":[61],"letter,":[62],"we":[63,112,141],"design":[64],"method":[66,115],"integrates":[68],"RL":[69,78,124,139],"into":[71],"TAMP":[72,122,146],"pipelines.":[73],"Besides":[74],"policy,":[76],"skill":[79,89],"is":[80,100],"defined":[81],"data-driven":[83],"logical":[84],"components":[85],"enable":[87],"to":[90,102,147,158],"deployed":[92],"symbolic":[94],"planning.":[95],"A":[96],"plan":[97],"refinement":[98],"sub-routine":[99],"designed":[101],"further":[103],"tackle":[104],"inevitable":[106],"effect":[107],"experiments,":[111],"compare":[113],"our":[114],"baseline":[117],"hierarchical":[118],"from":[120],"both":[121],"fields":[125],"illustrate":[127],"strength":[129],"of":[130,145],"method.":[132],"The":[133],"results":[134],"show":[135],"embedding":[138],"skills,":[140,151],"extend":[142],"capability":[144],"domains":[148],"improve":[153],"efficiency":[156],"compared":[157],"previous":[160],"methods.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}