{"id":"https://openalex.org/W4365143376","doi":"https://doi.org/10.48550/arxiv.2304.04602","title":"Learning a Universal Human Prior for Dexterous Manipulation from Human Preference","display_name":"Learning a Universal Human Prior for Dexterous Manipulation from Human Preference","publication_year":2023,"publication_date":"2023-04-10","ids":{"openalex":"https://openalex.org/W4365143376","doi":"https://doi.org/10.48550/arxiv.2304.04602"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.04602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.04602","pdf_url":"https://arxiv.org/pdf/2304.04602","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.04602","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002742139","display_name":"Zihan Ding","orcid":"https://orcid.org/0009-0005-2008-4816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102989564","display_name":"Yuanpei Chen","orcid":"https://orcid.org/0000-0002-4674-553X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuanpei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000576583","display_name":"Allen Z. Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Allen Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061613634","display_name":"Shixiang Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Shixiang Shane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Qianxu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qianxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389358","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-9825-285X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101961985","display_name":"Chi Jin","orcid":"https://orcid.org/0000-0002-2865-5610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9908999800682068,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767076313495636},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7226237058639526},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6475690603256226},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6474639177322388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5948663949966431},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5930323600769043},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5861772894859314},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5255854725837708},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5045653581619263},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.42571085691452026},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.41504934430122375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33175647258758545},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09141805768013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767076313495636},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7226237058639526},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6475690603256226},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6474639177322388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5948663949966431},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5930323600769043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5861772894859314},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5255854725837708},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5045653581619263},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.42571085691452026},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.41504934430122375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33175647258758545},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09141805768013},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.04602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.04602","pdf_url":"https://arxiv.org/pdf/2304.04602","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2304.04602","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.04602","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.04602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.04602","pdf_url":"https://arxiv.org/pdf/2304.04602","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2782058284","https://openalex.org/W3103937890"],"abstract_inverted_index":{"Generating":[0],"human-like":[1,131],"behavior":[2,119],"on":[3,53,81,133],"robots":[4],"is":[5,21,98,113],"a":[6,60,64,90],"great":[7],"challenge":[8],"especially":[9],"in":[10,87,122,136],"dexterous":[11],"manipulation":[12,85],"tasks":[13,86,138],"with":[14,32],"robotic":[15],"hands.":[16],"Scripting":[17],"policies":[18,31,80],"from":[19,55],"scratch":[20],"intractable":[22],"due":[23],"to":[24,46],"the":[25,50,78,110,118,123],"high-dimensional":[26],"control":[27],"space,":[28],"and":[29,36,44,105],"training":[30],"reinforcement":[33],"learning":[34],"(RL)":[35],"manual":[37],"reward":[38,96],"engineering":[39],"can":[40],"also":[41],"be":[42],"hard":[43],"lead":[45],"unnatural":[47],"motions.":[48],"Leveraging":[49],"recent":[51],"progress":[52],"RL":[54,79],"Human":[56],"Feedback,":[57],"we":[58],"propose":[59],"framework":[61],"that":[62],"learns":[63],"universal":[65],"human":[66,70,92,107],"prior":[67],"using":[68],"direct":[69],"preference":[71,108],"feedback":[72],"over":[73,109],"videos,":[74],"for":[75,116],"efficiently":[76],"tuning":[77],"20":[82],"dual-hand":[83],"robot":[84,134],"simulation,":[88],"without":[89],"single":[91],"demonstration.":[93],"A":[94],"task-agnostic":[95],"model":[97],"trained":[99],"through":[100],"iteratively":[101],"generating":[102],"diverse":[103,137],"polices":[104,121],"collecting":[106],"trajectories;":[111],"it":[112],"then":[114],"applied":[115],"regularizing":[117],"of":[120],"fine-tuning":[124],"stage.":[125],"Our":[126],"method":[127],"empirically":[128],"demonstrates":[129],"more":[130],"behaviors":[132],"hands":[135],"including":[139],"even":[140],"unseen":[141],"tasks,":[142],"indicating":[143],"its":[144],"generalization":[145],"capability.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2023-04-13T00:00:00"}