{"id":"https://openalex.org/W4285036494","doi":"https://doi.org/10.1109/icra46639.2022.9811963","title":"Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning","display_name":"Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285036494","doi":"https://doi.org/10.1109/icra46639.2022.9811963"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811963","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 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/A5085327057","display_name":"Jun Jin","orcid":"https://orcid.org/0000-0002-4295-502X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun Jin","raw_affiliation_strings":["Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada","Department of Computing Science, University of Alberta, Edmonton, AB., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101753111","display_name":"Daniel Graves","orcid":"https://orcid.org/0000-0002-5345-6584"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel Graves","raw_affiliation_strings":["Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046273482","display_name":"Cameron Haigh","orcid":"https://orcid.org/0009-0004-5557-8042"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cameron Haigh","raw_affiliation_strings":["Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106731907","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0002-2032-0381"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun Luo","raw_affiliation_strings":["Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada, Ltd.,Noah's Ark Lab,Edmonton,AB.,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948380","display_name":"Martin J\u00e4gersand","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Jagersand","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,AB.,Canada","Department of Computing Science, University of Alberta, Edmonton, AB., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,AB.,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB., Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7538,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8423224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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":0.9919999837875366,"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":0.9919999837875366,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.967700719833374},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8178133368492126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6720404624938965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987975597381592},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5692653059959412},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.540688693523407},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4635410010814667},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.45645496249198914},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.42510128021240234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41752496361732483},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3344191908836365},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.21269303560256958},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09679177403450012}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.967700719833374},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8178133368492126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720404624938965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987975597381592},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5692653059959412},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.540688693523407},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4635410010814667},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.45645496249198914},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.42510128021240234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41752496361732483},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3344191908836365},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.21269303560256958},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09679177403450012},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811963","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 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":80,"referenced_works":["https://openalex.org/W1564670092","https://openalex.org/W1959608418","https://openalex.org/W1966487689","https://openalex.org/W2075962208","https://openalex.org/W2111691855","https://openalex.org/W2119885245","https://openalex.org/W2125663122","https://openalex.org/W2132622533","https://openalex.org/W2139637968","https://openalex.org/W2153791616","https://openalex.org/W2169300227","https://openalex.org/W2203345135","https://openalex.org/W2526166478","https://openalex.org/W2575705757","https://openalex.org/W2605458966","https://openalex.org/W2741122588","https://openalex.org/W2767050701","https://openalex.org/W2781726626","https://openalex.org/W2806130867","https://openalex.org/W2809668646","https://openalex.org/W2892557643","https://openalex.org/W2894889845","https://openalex.org/W2895453875","https://openalex.org/W2909718913","https://openalex.org/W2938807566","https://openalex.org/W2942608247","https://openalex.org/W2950268955","https://openalex.org/W2962746398","https://openalex.org/W2963864421","https://openalex.org/W2963940579","https://openalex.org/W2964227158","https://openalex.org/W2967355195","https://openalex.org/W2968095426","https://openalex.org/W2968116426","https://openalex.org/W2972414681","https://openalex.org/W2974295111","https://openalex.org/W2984168904","https://openalex.org/W2990708646","https://openalex.org/W2995298643","https://openalex.org/W3004186391","https://openalex.org/W3012514211","https://openalex.org/W3020712699","https://openalex.org/W3022566517","https://openalex.org/W3090832832","https://openalex.org/W3101442004","https://openalex.org/W3104462930","https://openalex.org/W3206042616","https://openalex.org/W3206880326","https://openalex.org/W4288333940","https://openalex.org/W4288363736","https://openalex.org/W4289294484","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6633756471","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6675999342","https://openalex.org/W6679365036","https://openalex.org/W6684663846","https://openalex.org/W6684921986","https://openalex.org/W6687803322","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6749115525","https://openalex.org/W6752338937","https://openalex.org/W6752431149","https://openalex.org/W6754615820","https://openalex.org/W6754957883","https://openalex.org/W6756256016","https://openalex.org/W6761327112","https://openalex.org/W6764793234","https://openalex.org/W6767015469","https://openalex.org/W6770307204","https://openalex.org/W6771179988","https://openalex.org/W6771217966","https://openalex.org/W6772963868","https://openalex.org/W6774733536","https://openalex.org/W6776438516","https://openalex.org/W6785996349"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4225619808","https://openalex.org/W4388926065","https://openalex.org/W4376223516","https://openalex.org/W4226042081","https://openalex.org/W4283712691","https://openalex.org/W4302791885","https://openalex.org/W4308935744"],"abstract_inverted_index":{"We":[0,18,40,63,89],"consider":[1],"real-world":[2,123,132],"reinforcement":[3,81],"learning":[4,78,82],"(RL)":[5],"of":[6,50,130],"robotic":[7],"manipulation":[8],"tasks":[9],"that":[10,24,55,65,91,102,111],"involve":[11],"both":[12],"visuomotor":[13],"skills":[14],"and":[15,30,99,106,122],"contact-rich":[16,116],"skills.":[17],"aim":[19],"to":[20,32,42,46],"train":[21],"a":[22,33,48,85,97],"policy":[23,77],"maps":[25],"multimodal":[26],"sensory":[27],"observations":[28],"(vision":[29],"force)":[31],"manipulator's":[34],"joint":[35],"velocities":[36],"under":[37],"practical":[38],"considerations.":[39],"propose":[41],"use":[43],"offline":[44,68],"samples":[45],"learn":[47],"set":[49],"general":[51],"value":[52],"functions":[53],"(GVFs)":[54],"make":[56],"counterfactual":[57,70,94],"predictions":[58,71,95],"from":[59],"the":[60,67,92,131],"visual":[61],"inputs.":[62],"show":[64],"combining":[66],"learned":[69,93],"with":[72],"force":[73],"feedbacks":[74],"in":[75,120],"online":[76,113],"allows":[79],"efficient":[80],"given":[83],"only":[84],"terminal":[86],"(success/failure)":[87],"reward.":[88],"argue":[90],"form":[96],"compact":[98],"informative":[100],"representation":[101],"enables":[103],"sample":[104],"efficiency":[105],"provides":[107],"auxiliary":[108],"reward":[109],"signals":[110],"guide":[112],"explorations":[114],"towards":[115],"states.":[117],"Various":[118],"experiments":[119],"simulation":[121],"settings":[124],"were":[125],"performed":[126],"for":[127],"evaluation.":[128],"Recordings":[129],"robot":[133],"training":[134],"can":[135],"be":[136],"found":[137],"via":[138],"https://sites.google.com/view/realrl.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}