{"id":"https://openalex.org/W4416748646","doi":"https://doi.org/10.1109/iros60139.2025.11247025","title":"ACGD: Visual Multitask Policy Learning with Asymmetric Critic Guided Distillation","display_name":"ACGD: Visual Multitask Policy Learning with Asymmetric Critic Guided Distillation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748646","doi":"https://doi.org/10.1109/iros60139.2025.11247025"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5056595724","display_name":"Krishnan Srinivasan","orcid":"https://orcid.org/0000-0002-0673-1643"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnan Srinivasan","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101368876","display_name":"Jie Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Henry Ang","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Ang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073253090","display_name":"Eric Heiden","orcid":"https://orcid.org/0000-0002-2031-8564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Heiden","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108257764","display_name":"Dieter Fox","orcid":"https://orcid.org/0009-0009-4694-9127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dieter Fox","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021676288","display_name":"Jeannette Bohg","orcid":"https://orcid.org/0000-0002-4921-7193"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeannette Bohg","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49175724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6384999752044678,"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":0.6384999752044678,"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":0.31029999256134033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.011900000274181366,"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":0.7296000123023987},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.44699999690055847},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40610000491142273},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4018999934196472},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38260000944137573},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.374099999666214},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3732999861240387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7296000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610999703407288},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5157999992370605},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.44699999690055847},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2784999907016754},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3093922502","https://openalex.org/W4312326293","https://openalex.org/W4383108265","https://openalex.org/W4383108784","https://openalex.org/W4385430674","https://openalex.org/W4386071465","https://openalex.org/W4388901983","https://openalex.org/W4399563712","https://openalex.org/W4401416041","https://openalex.org/W4402660103","https://openalex.org/W4415800339"],"related_works":[],"abstract_inverted_index":{"We":[0,149],"present":[1],"Asymmetric":[2],"Critic":[3],"Guided":[4],"Distillation,":[5],"ACGD,":[6],"a":[7,26,41,111,137,152,167],"framework":[8],"for":[9,47,126,184],"learning":[10,142,146],"multi-task":[11,44,117,155],"dexterous":[12,48,156],"manipulation":[13,157],"policies":[14,39,52],"that":[15,31,97],"can":[16],"manipulate":[17],"articulated":[18],"objects":[19],"using":[20,84],"images":[21,87],"as":[22],"input.":[23],"ACGD":[24],"is":[25],"scalable":[27],"student-teacher":[28],"distillation":[29],"approach":[30,131],"utilizes":[32],"behavior":[33],"cloning":[34],"to":[35,61,104,136],"distill":[36],"multiple":[37],"expert":[38,51],"into":[40],"single":[42],"vision-based,":[43],"student":[45,76],"policy":[46,77],"manipulation.":[49],"The":[50],"are":[53],"trained":[54],"with":[55,59,174],"traditional":[56],"RL":[57],"techniques":[58],"access":[60],"privileged":[62],"state":[63],"information":[64],"of":[65,139,154],"both":[66],"the":[67,70,74,106,116,178],"robot":[68,89],"and":[69,88,101,144,166,170],"manipulated":[71],"object,":[72],"while":[73],"distilled":[75],"operates":[78],"under":[79],"realistic":[80],"sensory":[81],"constraints,":[82],"specifically":[83],"only":[85],"camera":[86],"proprioception.":[90],"During":[91],"distillation,":[92],"we":[93,119],"use":[94],"an":[95,123],"expert-critic":[96],"provides":[98],"action":[99,108],"labels":[100],"value":[102],"estimates":[103],"refine":[105],"student\u2019s":[107],"sampling":[109],"through":[110,122],"dual":[112],"IL/RL":[113],"objective.":[114],"In":[115],"setting,":[118],"achieve":[120],"this":[121],"aggregate":[124],"critic":[125],"different":[127],"single-task":[128],"experts.":[129],"Our":[130],"exhibits":[132],"strong":[133],"performance":[134,173],"compared":[135],"number":[138],"state-of-the-art":[140,172],"imitation":[141],"(IL)":[143],"reinforcement":[145],"(RL)":[147],"baselines.":[148],"evaluate":[150],"across":[151],"variety":[153],"benchmarks":[158],"including":[159],"bimanual":[160],"manipulation,":[161],"single-hand":[162],"object":[163],"articulation":[164],"tasks,":[165],"tendon-actuated":[168],"hand":[169],"achieves":[171],"10-15%":[175],"improvement":[176],"over":[177],"baseline":[179],"algorithms.":[180],"Visit":[181],"our":[182],"website":[183],"more":[185],"details.":[186]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}