{"id":"https://openalex.org/W4362722144","doi":"https://doi.org/10.1109/icra48891.2023.10161178","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","display_name":"Learning Reward Functions for Robotic Manipulation by Observing Humans","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4362722144","doi":"https://doi.org/10.1109/icra48891.2023.10161178"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161178","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":"preprint","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/A5022706238","display_name":"Minttu Alakuijala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI"],"is_corresponding":true,"raw_author_name":"Minttu Alakuijala","raw_affiliation_strings":["Inria,ENS-PSL, CNRS,Département d'informatique de l'Ecole normale supérieure"],"affiliations":[{"raw_affiliation_string":"Inria,ENS-PSL, CNRS,Département d'informatique de l'Ecole normale supérieure","institution_ids":["https://openalex.org/I4210103330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008880429","display_name":"Gabriel Dulac-Arnold","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Dulac-Arnold","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062817741","display_name":"Julien Mairal","orcid":"https://orcid.org/0000-0001-6991-2110"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Mairal","raw_affiliation_strings":["Univ. Grenoble Alpes, Inria,CNRS, Grenoble INP, LJK,Grenoble,France,38000"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Inria,CNRS, Grenoble INP, LJK,Grenoble,France,38000","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I4210149092","https://openalex.org/I1294671590","https://openalex.org/I106785703","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109535575","display_name":"Jean Ponce","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]},{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}],"countries":["BI","US"],"is_corresponding":false,"raw_author_name":"Jean Ponce","raw_affiliation_strings":["Inria,ENS-PSL, CNRS,Département d'informatique de l'Ecole normale supérieure","Center for Data Science, Courant Institute of Mathematical Sciences, New York University"],"affiliations":[{"raw_affiliation_string":"Inria,ENS-PSL, CNRS,Département d'informatique de l'Ecole normale supérieure","institution_ids":["https://openalex.org/I4210103330"]},{"raw_affiliation_string":"Center for Data Science, Courant Institute of Mathematical Sciences, New York University","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022706238"],"corresponding_institution_ids":["https://openalex.org/I4210103330"],"apc_list":null,"apc_paid":null,"fwci":3.73279651,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91018222,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5006","last_page":"5012"},"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695072889328003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6879803538322449},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6556107997894287},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6364130973815918},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6363252997398376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5968630313873291},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5622532367706299},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49855923652648926},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4424174726009369},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42827239632606506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38970327377319336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695072889328003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6879803538322449},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6556107997894287},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6364130973815918},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6363252997398376},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5968630313873291},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5622532367706299},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49855923652648926},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4424174726009369},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42827239632606506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38970327377319336},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161178","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":69,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2051228319","https://openalex.org/W2194775991","https://openalex.org/W2605102758","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2769112066","https://openalex.org/W2781726626","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2947150733","https://openalex.org/W2952854274","https://openalex.org/W2962736495","https://openalex.org/W2962760690","https://openalex.org/W2962787969","https://openalex.org/W2963277051","https://openalex.org/W2963703448","https://openalex.org/W2978455699","https://openalex.org/W2981344907","https://openalex.org/W2991355586","https://openalex.org/W3009295642","https://openalex.org/W3035198432","https://openalex.org/W3037440645","https://openalex.org/W3094502228","https://openalex.org/W3102502242","https://openalex.org/W3115080916","https://openalex.org/W3122520957","https://openalex.org/W3175995235","https://openalex.org/W3189615635","https://openalex.org/W3204665606","https://openalex.org/W3205423339","https://openalex.org/W3205786327","https://openalex.org/W3207832698","https://openalex.org/W4214612132","https://openalex.org/W4221159977","https://openalex.org/W4224308101","https://openalex.org/W4287599290","https://openalex.org/W4288280943","https://openalex.org/W4292779060","https://openalex.org/W4300198501","https://openalex.org/W4302010007","https://openalex.org/W4306882122","https://openalex.org/W4312735840","https://openalex.org/W4321147108","https://openalex.org/W4321153853","https://openalex.org/W4323640751","https://openalex.org/W6638088447","https://openalex.org/W6718092244","https://openalex.org/W6747473740","https://openalex.org/W6751661917","https://openalex.org/W6751955673","https://openalex.org/W6754484421","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6768831546","https://openalex.org/W6769596995","https://openalex.org/W6771270455","https://openalex.org/W6778883912","https://openalex.org/W6780159193","https://openalex.org/W6784212503","https://openalex.org/W6784333009","https://openalex.org/W6784862516","https://openalex.org/W6787566416","https://openalex.org/W6796242396","https://openalex.org/W6802366246","https://openalex.org/W6810080435","https://openalex.org/W6810081322","https://openalex.org/W6845793730","https://openalex.org/W6955071965"],"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/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Observing":[0],"a":[1,7,26,34,51,59,85,94,112,135,146,169,177,184,203,211],"human":[2,23,155,181],"demonstrator":[3],"manipulate":[4],"objects":[5],"provides":[6],"rich,":[8],"scalable":[9],"and":[10,38,90,119],"inexpensive":[11],"source":[12],"of":[13,48,54,71,148,179,187,198],"data":[14,171],"for":[15,63,97,107],"learning":[16],"robotic":[17,27,64],"policies.":[18,66],"However,":[19],"transferring":[20],"skills":[21],"from":[22,84,172,215],"videos":[24,47,156],"to":[25,57,68,81,92,111,141,157,195,208],"manipulator":[28],"poses":[29],"several":[30,199],"challenges,":[31],"not":[32],"least":[33],"difference":[35],"in":[36,100,122],"action":[37],"observation":[39],"spaces.":[40],"In":[41],"this":[42,72],"work,":[43],"we":[44,138],"use":[45],"unlabeled":[46],"humans":[49],"solving":[50],"wide":[52],"range":[53],"manipulation":[55,65,200],"tasks":[56,201],"learn":[58],"task-agnostic":[60],"reward":[61,77,213],"function":[62,78,133],"Thanks":[67],"the":[69,75,132,173],"diversity":[70],"training":[73,197],"data,":[74],"learned":[76],"sufficiently":[79],"generalizes":[80],"image":[82],"observations":[83],"previously":[86],"unseen":[87],"robot":[88,174,205],"embodiment":[89],"environment":[91],"provide":[93],"meaningful":[95],"prior":[96,151],"directed":[98],"exploration":[99],"reinforcement":[101],"learning.":[102,129],"We":[103],"propose":[104],"two":[105],"methods":[106],"scoring":[108],"states":[109],"relative":[110],"goal":[113,136],"image:":[114],"through":[115,120],"direct":[116],"temporal":[117],"regression,":[118],"distances":[121],"an":[123],"embedding":[124],"space":[125],"obtained":[126,214],"with":[127],"time-contrastive":[128],"By":[130],"conditioning":[131],"on":[134,153,202],"image,":[137],"are":[139],"able":[140,194],"reuse":[142],"one":[143],"model":[144],"across":[145,189],"variety":[147],"tasks.":[149],"Unlike":[150],"work":[152],"leveraging":[154],"teach":[158],"robots,":[159],"our":[160],"method,":[161],"Human":[162],"Offline":[163],"Learned":[164],"Distances":[165],"(HOLD)":[166],"requires":[167],"neither":[168],"priori":[170],"environment,":[175],"nor":[176,183],"set":[178],"task-specific":[180],"demonstrations,":[182],"predefined":[185],"notion":[186],"correspondence":[188],"morphologies,":[190],"yet":[191],"it":[192],"is":[193],"accelerate":[196],"simulated":[204],"arm":[206],"compared":[207],"using":[209],"only":[210],"sparse":[212],"task":[216],"completion.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}