{"id":"https://openalex.org/W4413926107","doi":"https://doi.org/10.1109/icra55743.2025.11128466","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","display_name":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413926107","doi":"https://doi.org/10.1109/icra55743.2025.11128466"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5050593664","display_name":"Ond\u0159ej B\u00ed\u017ea","orcid":"https://orcid.org/0000-0003-3390-8050"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ondrej Biza","raw_affiliation_strings":["Robotics and AI Institute (Boston Dynamics AI Institute LLC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute (Boston Dynamics AI Institute LLC)","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086102153","display_name":"Thomas Weng","orcid":"https://orcid.org/0000-0002-0874-6507"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Weng","raw_affiliation_strings":["Robotics and AI Institute (Boston Dynamics AI Institute LLC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute (Boston Dynamics AI Institute LLC)","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109517866","display_name":"Lingfeng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingfeng Sun","raw_affiliation_strings":["Robotics and AI Institute (Boston Dynamics AI Institute LLC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute (Boston Dynamics AI Institute LLC)","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049609650","display_name":"Karl Schmeckpeper","orcid":"https://orcid.org/0000-0003-4989-2022"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Schmeckpeper","raw_affiliation_strings":["Robotics and AI Institute (Boston Dynamics AI Institute LLC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute (Boston Dynamics AI Institute LLC)","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022064886","display_name":"Tarik Kele\u015ftemur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarik Kelestemur","raw_affiliation_strings":["Robotics and AI Institute (Boston Dynamics AI Institute LLC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute (Boston Dynamics AI Institute LLC)","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063425598","display_name":"Yecheng Jason Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yecheng Jason Ma","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103163468","display_name":"Robert Platt","orcid":"https://orcid.org/0009-0001-2033-3473"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Platt","raw_affiliation_strings":["Robotics and AI Institute (Boston Dynamics AI Institute LLC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute (Boston Dynamics AI Institute LLC)","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073129092","display_name":"Jan-Willem van de Meent","orcid":"https://orcid.org/0000-0001-9465-5398"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jan-Willem van de Meent","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032791503","display_name":"Lawson L. S. Wong","orcid":"https://orcid.org/0000-0002-9944-7587"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawson L.S. Wong","raw_affiliation_strings":["Northeastern University, Khoury College of Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Khoury College of Computer Sciences","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5050593664"],"corresponding_institution_ids":["https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11488824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4797","last_page":"4805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9042999744415283,"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":0.9042999744415283,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7684807777404785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891485452651978},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5338984727859497},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.44401898980140686},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4402187168598175},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4379648268222809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4142149090766907},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.22705882787704468},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17483362555503845},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04734012484550476}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7684807777404785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891485452651978},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5338984727859497},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.44401898980140686},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4402187168598175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4379648268222809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4142149090766907},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.22705882787704468},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17483362555503845},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04734012484550476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8696985551","display_name":null,"funder_award_id":"1750649,2107256,2314182,2409351","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2583137229","https://openalex.org/W2769112066","https://openalex.org/W2798897443","https://openalex.org/W2938421504","https://openalex.org/W3038298277","https://openalex.org/W3108330043","https://openalex.org/W3122520957","https://openalex.org/W3189615635","https://openalex.org/W3204657926","https://openalex.org/W3205786327","https://openalex.org/W4221161303","https://openalex.org/W4283788863","https://openalex.org/W4312903454","https://openalex.org/W4386065350","https://openalex.org/W4390874575","https://openalex.org/W4401415522","https://openalex.org/W4401416214","https://openalex.org/W4401416531","https://openalex.org/W4402354047","https://openalex.org/W4402354084","https://openalex.org/W4402727916","https://openalex.org/W4404612908"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"the":[4,16,103,138],"potential":[5],"to":[6,9,31,82,154,162],"enable":[7],"robots":[8,188],"learn":[10],"from":[11,36,181],"their":[12],"own":[13],"actions":[14],"in":[15,25,125,137],"real":[17,139],"world.":[18],"Unfortunately,":[19],"RL":[20,161],"can":[21,66,86],"be":[22,67],"prohibitively":[23],"expensive,":[24],"terms":[26],"of":[27,183,186],"on-robot":[28],"runtime,":[29],"due":[30],"inefficient":[32],"exploration":[33],"when":[34,106],"learning":[35,63,173],"a":[37,59,108,112,142,146,155,190],"sparse":[38],"reward":[39,43,61,104,172],"signal.":[40],"Designing":[41],"dense":[42,60],"functions":[44],"is":[45,80],"labour-intensive":[46],"and":[47,111,119,131,145,185],"requires":[48],"domain":[49],"expertise.":[50],"In":[51],"our":[52,78,170],"work,":[53],"we":[54,85],"propose":[55],"Goal-Contrastive":[56],"Rewards":[57],"(GCR),":[58],"function":[62,99],"method":[64,79],"that":[65,100,115,151],"trained":[68],"on":[69],"passive":[70],"video":[71],"demonstrations.":[72],"By":[73],"using":[74,141],"videos":[75,182],"without":[76],"actions,":[77],"easier":[81],"scale,":[83],"as":[84,134,136,166,169],"use":[87],"arbitrary":[88],"videos.":[89],"GCR":[90,152],"combines":[91],"two":[92],"loss":[93,98,114],"functions,":[94],"an":[95],"implicit":[96],"value":[97],"models":[101],"how":[102],"increases":[105],"traversing":[107],"successful":[109,118],"trajectory,":[110],"goal-contrastive":[113],"discriminates":[116],"between":[117],"failed":[120],"trajectories.":[121],"We":[122,149,175],"perform":[123],"experiments":[124],"simulated":[126],"manipulation":[127],"environments":[128],"across":[129],"RoboMimic":[130],"MimicGen":[132],"tasks,":[133],"well":[135],"world":[140],"Franka":[143],"arm":[144],"Spot":[147],"quadruped.":[148],"find":[150],"leads":[153],"more-sample":[156],"efficient":[157],"RL,":[158],"enabling":[159],"model-free":[160],"solve":[163],"about":[164],"twice":[165],"many":[167],"tasks":[168],"baseline":[171],"methods.":[174],"also":[176],"demonstrate":[177],"positive":[178],"cross-embodiment":[179],"transfer":[180],"people":[184],"other":[187],"performing":[189],"task.":[191],"Website:":[192],"https://gcr-robot.github.io/.":[193]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}