{"id":"https://openalex.org/W7213499856","doi":"https://doi.org/10.48550/arxiv.2609.17682","title":"DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery","display_name":"DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213499856","doi":"https://doi.org/10.48550/arxiv.2609.17682"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17682","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17682","pdf_url":"https://arxiv.org/pdf/2609.17682","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.17682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152021470","display_name":"Sun Woo Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, Sun Woo","raw_affiliation_strings":["NVIDIA , Canada ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , Canada ,","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134856968","display_name":"Xue Bin Peng","orcid":"https://orcid.org/0000-0002-3677-5655","observed_orcids":["https://orcid.org/0000-0002-3677-5655"]},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peng, Xue Bin","raw_affiliation_strings":["Simon Fraser University , Canada ,","Simon Fraser University , Canada , and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University , Canada ,","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"Simon Fraser University , Canada , and","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12290","display_name":"Human Motion and Animation","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/skill-discovery","display_name":"skill discovery","score":0.9089999794960022},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7409999966621399},{"id":"https://openalex.org/keywords/score-matching","display_name":"score matching","score":0.8600000143051147},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"entropy estimation","score":0.6119999885559082},{"id":"https://openalex.org/keywords/skill-variety","display_name":"skill variety","score":0.3370000123977661},{"id":"https://openalex.org/keywords/humanoid-robot-control","display_name":"humanoid robot control","score":0.5720000267028809},{"id":"https://openalex.org/keywords/hierarchical-control","display_name":"hierarchical control","score":0.6110000014305115},{"id":"https://openalex.org/keywords/mutual-information-maximization","display_name":"mutual information maximization","score":0.5659999847412109},{"id":"https://openalex.org/keywords/behavioral-repertoire","display_name":"behavioral repertoire","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5544999837875366},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C169976356","wikidata":"https://www.wikidata.org/wiki/Q13208902","display_name":"Motor skill","level":2,"score":0.5},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284999966621399},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C137813230","wikidata":"https://www.wikidata.org/wiki/Q2996165","display_name":"Motor control","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C135796866","wikidata":"https://www.wikidata.org/wiki/Q7315328","display_name":"Reservoir computing","level":4,"score":0.27639999985694885},{"id":"https://openalex.org/C3019722297","wikidata":"https://www.wikidata.org/wiki/Q4440864","display_name":"High dimensional","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17682","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17682","pdf_url":"https://arxiv.org/pdf/2609.17682","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.17682","doi":"https://doi.org/10.48550/arxiv.2609.17682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17682","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.17682","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17682","pdf_url":"https://arxiv.org/pdf/2609.17682","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2090024711","display_name":null,"funder_award_id":"RGPIN-2015-04843","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3203192175","display_name":null,"funder_award_id":"04843","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G560051739","display_name":null,"funder_award_id":"RGPIN-2015","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213499856.pdf","grobid_xml":"https://content.openalex.org/works/W7213499856.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1990922788","https://openalex.org/W1990932462","https://openalex.org/W2010302808","https://openalex.org/W2042408133","https://openalex.org/W2043878167","https://openalex.org/W2072118986","https://openalex.org/W2073531546","https://openalex.org/W2076806230","https://openalex.org/W2094217503","https://openalex.org/W2120894402","https://openalex.org/W2123236823","https://openalex.org/W2133220762","https://openalex.org/W2140190473","https://openalex.org/W2534060593","https://openalex.org/W2556477470","https://openalex.org/W2568351494","https://openalex.org/W2736601468","https://openalex.org/W2788741142","https://openalex.org/W2796290181","https://openalex.org/W2899205164","https://openalex.org/W2899718839","https://openalex.org/W2949924544","https://openalex.org/W2954142106","https://openalex.org/W2958043083","https://openalex.org/W3048474702","https://openalex.org/W3147968035","https://openalex.org/W3153832461","https://openalex.org/W3193576605","https://openalex.org/W4214717370","https://openalex.org/W4240716940","https://openalex.org/W4386942321","https://openalex.org/W4392270829","https://openalex.org/W4400582082","https://openalex.org/W4403364958","https://openalex.org/W4403580245","https://openalex.org/W4407424290","https://openalex.org/W4415277455","https://openalex.org/W4416052352","https://openalex.org/W4417011590"],"related_works":["https://openalex.org/W4221153713","https://openalex.org/W4378513186","https://openalex.org/W6945719594","https://openalex.org/W2995736683","https://openalex.org/W4320830001","https://openalex.org/W7127414850","https://openalex.org/W4200633611","https://openalex.org/W3210157506","https://openalex.org/W4414982584","https://openalex.org/W4417214537"],"abstract_inverted_index":{"Humans":[0],"efficiently":[1,30],"learn":[2],"new":[3,32],"tasks":[4,33],"by":[5,34,76,88],"reusing":[6],"a":[7,41,89,171,177,203,225,244],"rich":[8],"repertoire":[9,49,246],"of":[10,44,54,133,145,185,199,206,247,260],"motor":[11,37,249],"skills":[12,74,151,200,214,250],"across":[13,269],"different":[14],"goals":[15],"and":[16,61,84,156,229,262],"contexts.":[17],"A":[18,67],"similar":[19],"strategy":[20],"can":[21,266],"also":[22],"be":[23,51,267],"used":[24,69],"to":[25,29,180,257],"enable":[26],"simulated":[27],"characters":[28],"perform":[31],"leveraging":[35],"reusable":[36,248],"skills.":[38],"To":[39],"support":[40],"wide":[42],"range":[43,205],"downstream":[45,160,219,270],"tasks,":[46],"the":[47,78,85,100,112,134,146,182,186,197,258],"learned":[48,213],"should":[50],"diverse,":[52],"consisting":[53],"distinct":[55],"behaviors":[56,105,207,264],"as":[57,59],"well":[58],"spatial":[60],"temporal":[62],"variation":[63],"within":[64],"each":[65,107],"behavior.":[66],"commonly":[68],"method":[70,174],"for":[71,159,208],"learning":[72],"diverse":[73],"is":[75,116],"maximizing":[77],"mutual":[79],"information":[80],"between":[81],"skill":[82,172,253],"latents":[83],"states":[86],"produced":[87],"policy.":[90],"The":[91,193,212],"marginal":[92,113],"state":[93,114,135,147,188],"entropy":[94,102,115,183],"promotes":[95],"broad":[96,143],"behavioral":[97,154],"coverage,":[98],"while":[99],"conditional":[101],"encourages":[103,196],"consistent":[104],"from":[106,235],"latent.":[108],"However,":[109],"directly":[110],"estimating":[111],"intractable":[117],"in":[118,150,217],"high-dimensional":[119,209],"control":[120,220,223,231],"problems.":[121],"Prior":[122],"methods":[123],"therefore":[124],"rely":[125],"on":[126],"indirect":[127],"latent-space":[128],"approximations":[129,138],"or":[130],"coarse":[131],"estimators":[132],"distribution.":[136],"These":[137],"may":[139],"not":[140],"effectively":[141],"promote":[142],"coverage":[144],"space,":[148],"resulting":[149,194],"with":[152,224],"limited":[153],"diversity":[155],"reduced":[157],"utility":[158],"tasks.":[161,271],"In":[162],"this":[163],"work,":[164],"we":[165],"propose":[166],"Diffusion":[167],"Skill":[168],"Discovery":[169],"(DSD),":[170],"discovery":[173,198,254],"that":[175,201,241,265],"uses":[176],"diffusion":[178],"model":[179],"approximate":[181],"gradient":[184],"policy-induced":[187],"distribution":[189],"through":[190,232],"score":[191],"matching.":[192],"objective":[195],"produce":[202],"broader":[204,245],"humanoid":[210],"control.":[211],"are":[215],"reused":[216,268],"two":[218],"settings:":[221],"hierarchical":[222],"task-specific":[226],"high-level":[227],"policy":[228],"zero-shot":[230],"latent":[233],"selection":[234],"offline":[236],"trajectories.":[237],"Our":[238],"experiments":[239],"show":[240],"DSD":[242],"discovers":[243],"than":[251],"prior":[252],"methods,":[255],"leading":[256],"emergence":[259],"complex":[261],"agile":[263]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-18T00:00:00"}