{"id":"https://openalex.org/W4386028505","doi":"https://doi.org/10.3390/robotics12040119","title":"MURM: Utilization of Multi-Views for Goal-Conditioned Reinforcement Learning in Robotic Manipulation","display_name":"MURM: Utilization of Multi-Views for Goal-Conditioned Reinforcement Learning in Robotic Manipulation","publication_year":2023,"publication_date":"2023-08-19","ids":{"openalex":"https://openalex.org/W4386028505","doi":"https://doi.org/10.3390/robotics12040119"},"language":"en","primary_location":{"id":"doi:10.3390/robotics12040119","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/robotics12040119","pdf_url":"https://www.mdpi.com/2218-6581/12/4/119/pdf?version=1692581074","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2218-6581/12/4/119/pdf?version=1692581074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031539899","display_name":"Seongwon Jang","orcid":"https://orcid.org/0000-0002-9796-5743"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongwon Jang","raw_affiliation_strings":["Mechanical Engineering Department, Yonsei University, Seoul 03722, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9796-5743","affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Yonsei University, Seoul 03722, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027146105","display_name":"Hyemi Jeong","orcid":"https://orcid.org/0000-0002-3486-1082"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyemi Jeong","raw_affiliation_strings":["Mechanical Engineering Department, Yonsei University, Seoul 03722, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3486-1082","affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Yonsei University, Seoul 03722, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045165772","display_name":"Hyunseok Yang","orcid":"https://orcid.org/0000-0002-1872-7449"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyunseok Yang","raw_affiliation_strings":["Mechanical Engineering Department, Yonsei University, Seoul 03722, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, Yonsei University, Seoul 03722, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045165772"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.1704,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55874074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":"4","first_page":"119","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7970503568649292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.732022762298584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6439881324768066},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.567341148853302},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5161858201026917},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4932484030723572},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4857800304889679},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45856133103370667},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4356890916824341},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4348798394203186},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3931308388710022},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.16737425327301025}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7970503568649292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732022762298584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6439881324768066},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.567341148853302},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5161858201026917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4932484030723572},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4857800304889679},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45856133103370667},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4356890916824341},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4348798394203186},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3931308388710022},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.16737425327301025},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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":3,"locations":[{"id":"doi:10.3390/robotics12040119","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/robotics12040119","pdf_url":"https://www.mdpi.com/2218-6581/12/4/119/pdf?version=1692581074","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:126e21657abf413e916942af67b672a2","is_oa":true,"landing_page_url":"https://doaj.org/article/126e21657abf413e916942af67b672a2","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics, Vol 12, Iss 4, p 119 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2218-6581/12/4/119/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/robotics12040119","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Robotics; Volume 12; Issue 4; Pages: 119","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/robotics12040119","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/robotics12040119","pdf_url":"https://www.mdpi.com/2218-6581/12/4/119/pdf?version=1692581074","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386028505.pdf","grobid_xml":"https://content.openalex.org/works/W4386028505.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2752796333","https://openalex.org/W2753738274","https://openalex.org/W2766447205","https://openalex.org/W2787938642","https://openalex.org/W2911602305","https://openalex.org/W2982130342","https://openalex.org/W3015437096","https://openalex.org/W3089931053","https://openalex.org/W3091703975","https://openalex.org/W3127352841","https://openalex.org/W3131554325","https://openalex.org/W3174849255","https://openalex.org/W3207837114","https://openalex.org/W4206684559","https://openalex.org/W4206944021","https://openalex.org/W4214603949","https://openalex.org/W4214902667","https://openalex.org/W4225947020","https://openalex.org/W4285601030","https://openalex.org/W4312282783","https://openalex.org/W6638018090","https://openalex.org/W6740801417","https://openalex.org/W6753060773","https://openalex.org/W6764969207","https://openalex.org/W6796163856"],"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":{"We":[0,81,102,164,222],"present":[1],"a":[2,21,25,60,73,107,116,139,146,199],"novel":[3],"framework,":[4],"multi-view":[5,211],"unified":[6],"reinforcement":[7,51,184],"learning":[8,135,185],"for":[9,24,157,168,179],"robotic":[10],"manipulation":[11],"(MURM),":[12],"which":[13],"efficiently":[14],"utilizes":[15],"multiple":[16],"camera":[17,171],"views":[18],"to":[19,27,77,84,88,144,155,160,213,234],"train":[20,156,165,214],"goal-conditioned":[22,216],"policy":[23,63,87,217],"robot":[26],"perform":[28],"complex":[29,236],"tasks.":[30,80],"The":[31],"MURM":[32,239],"framework":[33],"consists":[34],"of":[35,72],"three":[36,104],"main":[37],"phases:":[38],"(i)":[39],"demo":[40,55],"collection":[41,56],"from":[42],"an":[43,113],"expert,":[44],"(ii)":[45],"representation":[46,134,150],"learning,":[47],"and":[48,75,120,173,197,203,227],"(iii)":[49],"offline":[50,183],"learning.":[52],"In":[53,132,181],"the":[54,79,85,94,130,133,175,182,189,215,230],"phase,":[57,136,186],"we":[58,137,187],"design":[59],"scripted":[61],"expert":[62,86],"that":[64,125,151,206,229],"uses":[65],"privileged":[66],"information,":[67],"such":[68],"as":[69,96,98,194],"Cartesian":[70],"coordinates":[71],"target":[74],"goal,":[76],"solve":[78,235],"add":[82],"noise":[83],"provide":[89],"sufficient":[90],"interactive":[91],"information":[92],"about":[93],"environment,":[95,110],"well":[97],"suboptimal":[99],"behavioral":[100],"trajectories.":[101],"designed":[103],"tasks":[105],"in":[106,115,129,210,225],"Pybullet":[108],"simulation":[109,226],"including":[111],"placing":[112],"object":[114],"desired":[117],"goal":[118,220],"position":[119],"picking":[121],"up":[122],"various":[123],"objects":[124],"are":[126],"randomly":[127],"positioned":[128],"environment.":[131],"use":[138,188],"vector-quantized":[140],"variational":[141],"autoencoder":[142],"(VQVAE)":[143],"learn":[145],"more":[147],"structured":[148],"latent":[149],"makes":[152],"it":[153],"feasible":[154],"RL":[158],"compared":[159],"high-dimensional":[161],"raw":[162],"images.":[163,221],"VQVAE":[166],"models":[167],"each":[169],"distinct":[170],"view":[172],"define":[174],"best":[176],"viewpoint":[177],"settings":[178,212],"training.":[180],"Implicit":[190],"Q-learning":[191],"(IQL)":[192],"algorithm":[193],"our":[195],"baseline":[196,232],"introduce":[198],"separated":[200],"Q-functions":[201],"method":[202,205],"dropout":[204],"can":[207],"be":[208],"implemented":[209],"with":[218],"supervised":[219],"conduct":[223],"experiments":[224],"show":[228],"single-view":[231],"fails":[233],"tasks,":[237],"whereas":[238],"is":[240],"successful.":[241]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}