{"id":"https://openalex.org/W3126384422","doi":"https://doi.org/10.1109/icar53236.2021.9659344","title":"Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks","display_name":"Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W3126384422","doi":"https://doi.org/10.1109/icar53236.2021.9659344","mag":"3126384422"},"language":"en","primary_location":{"id":"doi:10.1109/icar53236.2021.9659344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659344","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/20809.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005034849","display_name":"Luca Marzari","orcid":"https://orcid.org/0000-0002-0069-0182"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luca Marzari","raw_affiliation_strings":["Department of Computer Science, University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011989897","display_name":"Ameya Pore","orcid":"https://orcid.org/0000-0001-7380-6118"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["ES","IT"],"is_corresponding":false,"raw_author_name":"Ameya Pore","raw_affiliation_strings":["Center of Research in Biomedical Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain","Department of Computer Science, University of Verona, Verona, Italy","cnica de Catalunya, Barcelona, Spain","Center of Research in Biomedical Engineering, Universitat Polit&#x00E8"],"affiliations":[{"raw_affiliation_string":"Center of Research in Biomedical Engineering, Universitat Politècnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]},{"raw_affiliation_string":"cnica de Catalunya, Barcelona, Spain","institution_ids":[]},{"raw_affiliation_string":"Center of Research in Biomedical Engineering, Universitat Polit&#x00E8","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072250553","display_name":"Diego Dall\u2019Alba","orcid":"https://orcid.org/0000-0002-7300-5975"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Diego Dall'Alba","raw_affiliation_strings":["Department of Computer Science, University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013549829","display_name":"Gerardo Arag\u00f3n-Camarasa","orcid":"https://orcid.org/0000-0003-3756-5569"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gerardo Aragon-Camarasa","raw_affiliation_strings":["Computer Vision and Autonomous group, School of Computing Science, University of Glasgow, Glasgow, UK"],"affiliations":[{"raw_affiliation_string":"Computer Vision and Autonomous group, School of Computing Science, University of Glasgow, Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045922629","display_name":"Alessandro Farinelli","orcid":"https://orcid.org/0000-0002-2592-5814"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Farinelli","raw_affiliation_strings":["Department of Computer Science, University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065107543","display_name":"Paolo Fiorini","orcid":"https://orcid.org/0000-0002-0711-8605"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Fiorini","raw_affiliation_strings":["Department of Computer Science, University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005034849"],"corresponding_institution_ids":["https://openalex.org/I119439378"],"apc_list":null,"apc_paid":null,"fwci":10.0539,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.99426446,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"640","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.8479664325714111},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.805114209651947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982825040817261},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7404792308807373},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6795239448547363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6677718758583069},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.48022136092185974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45790740847587585},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41324126720428467},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11941304802894592}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8479664325714111},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.805114209651947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982825040817261},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7404792308807373},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6795239448547363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6677718758583069},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.48022136092185974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45790740847587585},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41324126720428467},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11941304802894592},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icar53236.2021.9659344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659344","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:257517","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/20809.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:257517","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/20809.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4099999964237213,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332605","display_name":"Agricultural Research Service","ror":"https://ror.org/02d2m2044"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1592847719","https://openalex.org/W1931877416","https://openalex.org/W2150884987","https://openalex.org/W2397253692","https://openalex.org/W2575705757","https://openalex.org/W2733961795","https://openalex.org/W2741122588","https://openalex.org/W2774343553","https://openalex.org/W2789008106","https://openalex.org/W2803281228","https://openalex.org/W2809668646","https://openalex.org/W2907537824","https://openalex.org/W2949604932","https://openalex.org/W2950614095","https://openalex.org/W2962736495","https://openalex.org/W2962957031","https://openalex.org/W2963099939","https://openalex.org/W2964043796","https://openalex.org/W2964262254","https://openalex.org/W2971178512","https://openalex.org/W3003997138","https://openalex.org/W3037625705","https://openalex.org/W3037790619","https://openalex.org/W3091277626","https://openalex.org/W3099298343","https://openalex.org/W3111294788","https://openalex.org/W3112178754","https://openalex.org/W3204292263","https://openalex.org/W4226137952","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W6627932998","https://openalex.org/W6640174482","https://openalex.org/W6692846177","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6746722632","https://openalex.org/W6752089545","https://openalex.org/W6752431149","https://openalex.org/W6757380569","https://openalex.org/W6768977950","https://openalex.org/W6780058518","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W3048672182","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2065450024"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2,46],"(DRL)":[3],"is":[4,24,38],"emerging":[5],"as":[6,111],"a":[7,18,67,90,125,141,145,161],"promising":[8],"approach":[9],"to":[10,53,75,128,151,176],"generate":[11],"adaptive":[12],"behaviors":[13],"for":[14],"robotic":[15,44,149,179],"platforms.":[16],"However,":[17,64],"major":[19],"drawback":[20],"of":[21,32,61,70,169],"using":[22,185],"DRL":[23,117],"the":[25,59,130,173,177],"data-hungry":[26],"training":[27],"regime":[28],"that":[29,72,157],"requires":[30,66],"millions":[31],"trial":[33],"and":[34,98,114,133,147,155,181],"error":[35],"attempts,":[36],"which":[37],"impractical":[39],"when":[40],"running":[41],"experiments":[42],"on":[43,165],"systems.":[45],"from":[47],"Demonstrations":[48],"(LfD)":[49],"has":[50],"been":[51],"introduced":[52],"solve":[54],"this":[55],"issue":[56],"by":[57,124],"cloning":[58],"behavior":[60],"expert":[62,112],"demonstrations.":[63],"LfD":[65,166],"large":[68],"number":[69],"demonstrations":[71],"are":[73,82,109,121],"difficult":[74],"be":[76,102],"acquired":[77],"since":[78],"dedicated":[79],"complex":[80,96],"setups":[81],"required.":[83],"To":[84],"overcome":[85],"these":[86],"limitations,":[87],"we":[88,143],"propose":[89],"multi-subtask":[91],"reinforcement":[92],"learning":[93],"methodology":[94,154,163],"where":[95],"pick":[97,132,146],"place":[99,134,148],"tasks":[100],"can":[101],"decomposed":[103],"into":[104],"low-level":[105],"subtasks.":[106],"These":[107],"subtasks":[108,120],"parametrized":[110],"networks":[113],"learned":[115,174],"via":[116],"methods.":[118],"Trained":[119],"then":[122],"combined":[123],"high-level":[126],"choreographer":[127],"accomplish":[129],"intended":[131],"task":[135],"considering":[136],"different":[137],"initial":[138],"configurations.":[139],"As":[140],"testbed,":[142],"use":[144],"simulator":[150],"demonstrate":[152,182],"our":[153,158],"show":[156],"method":[159],"outperforms":[160],"benchmark":[162],"based":[164],"in":[167],"terms":[168],"sample-efficiency.":[170],"We":[171],"transfer":[172],"policy":[175],"real":[178],"system":[180],"robust":[183],"grasping":[184],"various":[186],"geometric-shaped":[187],"objects.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}