{"id":"https://openalex.org/W4413944794","doi":"https://doi.org/10.1109/icra55743.2025.11127630","title":"Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation","display_name":"Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413944794","doi":"https://doi.org/10.1109/icra55743.2025.11127630"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127630","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":"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/A5116592777","display_name":"Kun Wu","orcid":"https://orcid.org/0000-0003-2095-2140"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":["Syracuse University,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University,NY,USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611386","display_name":"Yichen Zhu","orcid":"https://orcid.org/0000-0003-3614-1537"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Zhu","raw_affiliation_strings":["Midea Group, AI Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group, AI Research Center,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004994159","display_name":"Jinming Li","orcid":"https://orcid.org/0000-0001-8906-9191"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Li","raw_affiliation_strings":["Shanghai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072205796","display_name":"Junjie Wen","orcid":"https://orcid.org/0000-0002-8377-8066"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wen","raw_affiliation_strings":["East China Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719043","display_name":"Ning Liu","orcid":"https://orcid.org/0000-0001-5733-1052"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Liu","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics,Beijing,China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102897990","display_name":"Zhiyuan Xu","orcid":"https://orcid.org/0000-0001-8955-8358"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Xu","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics,Beijing,China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101471522","display_name":"Jian Tang","orcid":"https://orcid.org/0000-0002-8283-1961"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics,Beijing,China","institution_ids":["https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8811","last_page":"8818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7813000082969666,"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":0.7813000082969666,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7321000099182129,"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/computer-science","display_name":"Computer science","score":0.6913874745368958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6669875383377075},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6454488635063171},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5368692278862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5264015197753906},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39288970828056335},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15059202909469604},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12633144855499268},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.12426260113716125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913874745368958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6669875383377075},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6454488635063171},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5368692278862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264015197753906},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39288970828056335},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15059202909469604},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12633144855499268},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.12426260113716125},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127630","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2760103357","https://openalex.org/W2995986219","https://openalex.org/W4312933868","https://openalex.org/W4383109488","https://openalex.org/W4385403811","https://openalex.org/W4385430497","https://openalex.org/W4385430679","https://openalex.org/W4385430825","https://openalex.org/W4390873275","https://openalex.org/W4401414095","https://openalex.org/W4401414111","https://openalex.org/W4401415287","https://openalex.org/W4402354007","https://openalex.org/W4402354045","https://openalex.org/W4402354047","https://openalex.org/W4402354140","https://openalex.org/W4402354155","https://openalex.org/W4402783855","https://openalex.org/W4403021114","https://openalex.org/W4403337227"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W4389443772","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W2548721895","https://openalex.org/W4303457083","https://openalex.org/W2373456246","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Learning":[0],"visuomotor":[1],"policy":[2],"for":[3,12,40,67],"multi-task":[4,73,156,219],"robotic":[5],"manipulation":[6,74],"has":[7],"been":[8],"a":[9,26,36,41,63,86,137,154,226],"long-standing":[10],"challenge":[11],"the":[13,20,51,91,102,186,193,208,222],"robotics":[14],"community.":[15],"The":[16,44],"difficulty":[17],"lies":[18],"in":[19,31,35,153],"diversity":[21],"of":[22,46,53,72,93,188,210],"action":[23,38,47,83,103],"space:":[24],"typically,":[25],"goal":[27],"can":[28],"be":[29],"accomplished":[30],"multiple":[32,119],"ways,":[33],"resulting":[34],"multimodal":[37],"distribution":[39,48],"single":[42],"task.":[43],"complexity":[45],"escalates":[49],"as":[50],"number":[52,187],"tasks":[54,189],"increases.":[55],"In":[56],"this":[57],"work,":[58],"we":[59],"propose":[60],"Discrete":[61,76,134,162,197],"Policy,":[62],"robot":[64,127],"learning":[65,92,218],"method":[66,114],"training":[68,157],"universal":[69],"agents":[70],"capable":[71],"skills.":[75],"Policy":[77,135,140,163,179,198,201],"employs":[78],"vector":[79],"quantization":[80],"to":[81,191,203],"map":[82],"sequences":[84],"into":[85,101],"discrete":[87],"latent":[88,223],"space,":[89],"facilitating":[90],"task-specific":[94],"codes.":[95],"These":[96],"codes":[97],"are":[98],"then":[99],"reconstructed":[100],"space":[104,224],"conditioned":[105],"on":[106,115],"observations":[107],"and":[108,118,125,142,149,180,199],"language":[109],"instruction.":[110],"We":[111,129],"evaluate":[112],"our":[113,132,211],"both":[116,123],"simulation":[117],"real-world":[120,155],"embodiments,":[121],"including":[122,146],"single-arm":[124],"bimanual":[126],"settings.":[128],"demonstrate":[130],"that":[131,169,217],"proposed":[133],"outperforms":[136],"well-established":[138],"Diffusion":[139,178,200],"baseline":[141],"many":[143],"state-of-the-art":[144],"approaches,":[145],"ACT,":[147],"Octo,":[148],"OpenVLA.":[150,184],"For":[151],"example,":[152],"setting":[158],"with":[159],"five":[160],"tasks,":[161],"achieves":[164],"an":[165],"average":[166],"success":[167],"rate":[168],"is":[170,225,235],"<tex":[171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{2":[173],"6":[174],"\\%}$</tex>":[175],"higher":[176,182],"than":[177,183],"15%":[181],"As":[185],"increases":[190],"12,":[192],"performance":[194],"gap":[195],"between":[196],"widens":[202],"32.5":[204],"%,":[205],"further":[206],"showcasing":[207],"advantages":[209],"approach.":[212],"Our":[213,233],"work":[214],"empirically":[215],"demonstrates":[216],"policies":[220],"within":[221],"vital":[227],"step":[228],"toward":[229],"achieving":[230],"general-purpose":[231],"agents.":[232],"project":[234],"at":[236],"https://discretepolicy.github.io.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}