{"id":"https://openalex.org/W4383108554","doi":"https://doi.org/10.1109/icra48891.2023.10160983","title":"Comparison of Model-Based and Model-Free Reinforcement Learning for Real-World Dexterous Robotic Manipulation Tasks","display_name":"Comparison of Model-Based and Model-Free Reinforcement Learning for Real-World Dexterous Robotic Manipulation Tasks","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108554","doi":"https://doi.org/10.1109/icra48891.2023.10160983"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160983","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018740582","display_name":"David Valencia","orcid":"https://orcid.org/0000-0001-5571-2142"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"David Valencia","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101146653","display_name":"John Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"John Jia","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030391400","display_name":"Raymond Li","orcid":"https://orcid.org/0000-0002-8868-7104"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Raymond Li","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104139089","display_name":"Alex Hayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Alex Hayashi","raw_affiliation_strings":["New Dexterity Research Group, The University of Auckland,New Zealand","New Dexterity Research Group, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092397651","display_name":"Megan Lecchi","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Megan Lecchi","raw_affiliation_strings":["New Dexterity Research Group, The University of Auckland,New Zealand","New Dexterity Research Group, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092397652","display_name":"Reuel Terezakis","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Reuel Terezakis","raw_affiliation_strings":["New Dexterity Research Group, The University of Auckland,New Zealand","New Dexterity Research Group, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056560052","display_name":"Trevor Gee","orcid":"https://orcid.org/0000-0001-5554-7300"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Trevor Gee","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043544803","display_name":"Minas Liarokapis","orcid":"https://orcid.org/0000-0002-6016-1477"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Minas Liarokapis","raw_affiliation_strings":["New Dexterity Research Group, The University of Auckland,New Zealand","New Dexterity Research Group, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"New Dexterity Research Group, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065146109","display_name":"Bruce A. MacDonald","orcid":"https://orcid.org/0000-0001-7602-8497"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Bruce A. MacDonald","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054709242","display_name":"Henry Williams","orcid":"https://orcid.org/0000-0003-4510-0219"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Henry Williams","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":2.4196,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90963336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"871","last_page":"878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9095445871353149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6849221587181091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.655340313911438},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5113086700439453},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5028795599937439},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4241729974746704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38735532760620117}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9095445871353149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849221587181091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.655340313911438},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5113086700439453},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5028795599937439},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4241729974746704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38735532760620117},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160983","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W144009021","https://openalex.org/W1520597402","https://openalex.org/W1579853615","https://openalex.org/W1820657498","https://openalex.org/W1949804828","https://openalex.org/W2019165997","https://openalex.org/W2064878003","https://openalex.org/W2117629901","https://openalex.org/W2121863487","https://openalex.org/W2127412976","https://openalex.org/W2128082316","https://openalex.org/W2161697934","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2416041116","https://openalex.org/W2564447680","https://openalex.org/W2575705757","https://openalex.org/W2785389871","https://openalex.org/W2787938642","https://openalex.org/W2892245714","https://openalex.org/W2901112449","https://openalex.org/W2904246096","https://openalex.org/W2907450337","https://openalex.org/W2920362155","https://openalex.org/W2923762280","https://openalex.org/W2950069298","https://openalex.org/W2962793652","https://openalex.org/W2962872206","https://openalex.org/W2963170432","https://openalex.org/W2963864421","https://openalex.org/W2968340082","https://openalex.org/W2969320674","https://openalex.org/W2981402159","https://openalex.org/W2990747716","https://openalex.org/W3031634197","https://openalex.org/W3048681560","https://openalex.org/W3088158297","https://openalex.org/W3088310808","https://openalex.org/W3092703335","https://openalex.org/W3120778962","https://openalex.org/W3122402852","https://openalex.org/W3127561923","https://openalex.org/W3128707967","https://openalex.org/W3163621993","https://openalex.org/W3189576409","https://openalex.org/W3206200647","https://openalex.org/W3206820790","https://openalex.org/W3214292597","https://openalex.org/W4206434057","https://openalex.org/W4224862098","https://openalex.org/W4287750003","https://openalex.org/W4288319859","https://openalex.org/W4293864724","https://openalex.org/W4297824641","https://openalex.org/W4298206671","https://openalex.org/W4319236569","https://openalex.org/W6683526187","https://openalex.org/W6728252718","https://openalex.org/W6737327832","https://openalex.org/W6748519856","https://openalex.org/W6748839928","https://openalex.org/W6751494529","https://openalex.org/W6757592117","https://openalex.org/W6760405395","https://openalex.org/W6762205405","https://openalex.org/W6764053384","https://openalex.org/W6768397756","https://openalex.org/W6773319185","https://openalex.org/W6781954596","https://openalex.org/W6784114212","https://openalex.org/W6795593625","https://openalex.org/W6798695132","https://openalex.org/W6802781623","https://openalex.org/W6810605635"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W2004958254"],"abstract_inverted_index":{"Model":[0],"Free":[1],"Reinforcement":[2,42],"Learning":[3,43],"(MFRL)":[4],"has":[5],"shown":[6],"significant":[7],"promise":[8],"for":[9,76,99],"learning":[10,135,148],"dexterous":[11,102],"robotic":[12,79],"manipulation":[13,103],"tasks,":[14],"at":[15],"least":[16],"in":[17,51,147,152],"simulation.":[18],"However,":[19],"the":[20,28,55,65,72,87,91,96,116,120,139,149,153],"high":[21],"number":[22],"of":[23,58,68,74,89,134,138],"samples,":[24],"as":[25,27,46,156],"well":[26],"long":[29],"training":[30,66,97],"times,":[31],"prevent":[32],"MFRL":[33,59],"from":[34,125],"scaling":[35],"to":[36,94],"complex":[37],"real-world":[38,101],"tasks.":[39,80,104],"Model-":[40],"Based":[41],"(MBRL)":[44],"emerges":[45],"a":[47,84,110],"potential":[48],"solution":[49],"that,":[50],"theory,":[52],"can":[53],"improve":[54,95],"data":[56],"efficiency":[57],"approaches.":[60],"This":[61,81],"could":[62],"drastically":[63],"reduce":[64],"time":[67,98],"MFRL,":[69],"and":[70,119],"increase":[71],"application":[73],"RL":[75],"real-":[77],"world":[78,155],"article":[82],"presents":[83],"study":[85],"on":[86,109],"feasibility":[88],"using":[90],"state-of-the-art":[92],"MBRL":[93,131],"two":[100],"The":[105,127],"evaluation":[106],"is":[107,132],"conducted":[108],"real":[111,154],"low-cost":[112],"robot":[113],"gripper":[114],"where":[115],"predictive":[117],"model":[118],"control":[121,150],"policy":[122,151],"are":[123],"learned":[124],"scratch.":[126],"results":[128],"indicate":[129],"that":[130],"capable":[133],"accurate":[136],"models":[137],"world,":[140],"but":[141],"does":[142],"not":[143],"show":[144],"clear":[145],"improvements":[146],"prior":[157],"literature":[158],"suggests":[159],"should":[160],"be":[161],"expected.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}