{"id":"https://openalex.org/W4328007461","doi":"https://doi.org/10.1109/lra.2023.3259681","title":"Visual Reinforcement Learning With Self-Supervised 3D Representations","display_name":"Visual Reinforcement Learning With Self-Supervised 3D Representations","publication_year":2023,"publication_date":"2023-03-20","ids":{"openalex":"https://openalex.org/W4328007461","doi":"https://doi.org/10.1109/lra.2023.3259681"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3259681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3259681","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5063722358","display_name":"Yanjie Ze","orcid":"https://orcid.org/0000-0001-8422-8923"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Yanjie Ze","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","University of California San Diego, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8422-8923","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086722753","display_name":"Nicklas Hansen","orcid":"https://orcid.org/0000-0001-9897-4003"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicklas Hansen","raw_affiliation_strings":["University of California San Diego, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9897-4003","affiliations":[{"raw_affiliation_string":"University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063957844","display_name":"Yinbo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinbo Chen","raw_affiliation_strings":["University of California San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079372832","display_name":"Mohit Jain","orcid":"https://orcid.org/0000-0001-8628-2069"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Jain","raw_affiliation_strings":["University of California San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424275","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0003-3150-778X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["University of California San Diego, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3150-778X","affiliations":[{"raw_affiliation_string":"University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063722358"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":4.4447,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95002433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":"5","first_page":"2890","last_page":"2897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9969000220298767,"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":0.9969000220298767,"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":0.996399998664856,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.7586479187011719},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7063027620315552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7017918825149536},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5536497831344604},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5467121601104736},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.47222402691841125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45426860451698303},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4510561227798462},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2754296064376831},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11392408609390259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586479187011719},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7063027620315552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7017918825149536},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5536497831344604},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5467121601104736},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.47222402691841125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45426860451698303},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4510561227798462},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2754296064376831},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11392408609390259},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3259681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3259681","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2063063134","https://openalex.org/W2128019145","https://openalex.org/W2155007355","https://openalex.org/W2772709170","https://openalex.org/W2963436578","https://openalex.org/W2973229164","https://openalex.org/W2990747716","https://openalex.org/W2995298643","https://openalex.org/W3009561768","https://openalex.org/W3010797203","https://openalex.org/W3015437096","https://openalex.org/W3046419021","https://openalex.org/W3089931053","https://openalex.org/W3091357794","https://openalex.org/W3105398283","https://openalex.org/W3134153520","https://openalex.org/W3175254947","https://openalex.org/W3175558129","https://openalex.org/W3196466825","https://openalex.org/W3203828408","https://openalex.org/W3205321526","https://openalex.org/W3207591725","https://openalex.org/W4206944021","https://openalex.org/W4221159977","https://openalex.org/W4226167593","https://openalex.org/W4295246696","https://openalex.org/W4298857966","https://openalex.org/W4320086404","https://openalex.org/W6637967152","https://openalex.org/W6682849425","https://openalex.org/W6741977017","https://openalex.org/W6746177919","https://openalex.org/W6747473740","https://openalex.org/W6753060773","https://openalex.org/W6755305357","https://openalex.org/W6758420182","https://openalex.org/W6769596995","https://openalex.org/W6771217966","https://openalex.org/W6774670964","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6781203905","https://openalex.org/W6781494318","https://openalex.org/W6781776314","https://openalex.org/W6784098896","https://openalex.org/W6785551408","https://openalex.org/W6796163856","https://openalex.org/W6797309367","https://openalex.org/W6798071989","https://openalex.org/W6802704039","https://openalex.org/W6803519892","https://openalex.org/W6810080435","https://openalex.org/W6810536332","https://openalex.org/W6810655313","https://openalex.org/W6849110486"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4294770367"],"abstract_inverted_index":{"A":[0],"prominent":[1],"approach":[2],"to":[3,9,129,140],"visual":[4],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"is":[8,40,93,109],"learn":[10],"an":[11],"internal":[12],"state":[13],"representation":[14,108,131],"using":[15],"self-supervised":[16,67],"methods,":[17],"which":[18],"has":[19],"the":[20,37,107],"potential":[21],"benefit":[22],"of":[23,69,79],"improved":[24,125],"sample-efficiency":[25],"and":[26,32,100,150,159],"generalization":[27],"through":[28],"additional":[29],"learning":[30,68,132],"signal":[31],"inductive":[33],"biases.":[34],"However,":[35],"while":[36],"real":[38,142],"world":[39],"inherently":[41],"3D,":[42],"prior":[43],"efforts":[44],"have":[45],"largely":[46],"been":[47],"focused":[48],"on":[49,95,115],"leveraging":[50],"2D":[51,130],"computer":[52],"vision":[53],"techniques":[54],"as":[55],"auxiliary":[56],"self-supervision.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"present":[62],"a":[63,82,88,96,101,141],"unified":[64],"framework":[65,77],"for":[66,72],"3D":[70,91],"representations":[71],"motor":[73,153],"control.":[74],"Our":[75],"proposed":[76],"consists":[78],"two":[80],"phases:":[81],"<italic":[83,102,162],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[84,103,163],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">pretraining</i>":[85],"phase":[86,105],"where":[87,106],"deep":[89],"voxel-based":[90],"autoencoder":[92],"pretrained":[94],"large":[97],"object-centric":[98],"dataset,":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">finetuning</i>":[104],"jointly":[110],"finetuned":[111],"together":[112],"with":[113,145],"RL":[114],"in-domain":[116],"data.":[117],"We":[118],"empirically":[119],"show":[120],"that":[121,156],"our":[122,135],"method":[123],"enjoys":[124],"sample":[126],"efficiency":[127],"compared":[128],"methods.":[133],"Additionally,":[134],"learned":[136],"policies":[137],"transfer":[138],"zero-shot":[139],"robot":[143],"setup":[144],"only":[146],"approximate":[147],"geometric":[148],"correspondence,":[149],"successfully":[151],"solve":[152],"control":[154],"tasks":[155],"involve":[157],"grasping":[158],"lifting":[160],"from":[161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">a":[164],"single,":[165],"uncalibrated":[166],"RGB":[167],"camera</i>":[168],".":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}