{"id":"https://openalex.org/W7219155352","doi":null,"title":"DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation","display_name":"DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7219155352"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00360","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00360","pdf_url":"https://arxiv.org/pdf/2610.00360","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.00360","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5156527784","display_name":"Haoyu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Haoyu","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028696491","display_name":"Siyuan Qian","orcid":"https://orcid.org/0000-0002-7562-3689","observed_orcids":["https://orcid.org/0000-0002-7562-3689"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Siyuan","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156544699","display_name":"Yanjun Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yanjun","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156650347","display_name":"Zeyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zeyu","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145045144","display_name":"Yandong Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yandong","raw_affiliation_strings":["AI","Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI","institution_ids":[]},{"raw_affiliation_string":"Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156832621","display_name":"Boxin Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi, Boxin","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246","observed_orcids":["https://orcid.org/0000-0002-2077-1246","https://orcid.org/0000-0002-6973-8121"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Hao","raw_affiliation_strings":["School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9589999914169312,"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":0.9589999914169312,"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":0.0406000018119812,"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/T10982","display_name":"Motor Control and Adaptation","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dexterous-manipulation","display_name":"dexterous manipulation","score":0.968999981880188},{"id":"https://openalex.org/keywords/ppo","display_name":"PPO","score":0.5509999990463257},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.7570000290870667}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6040999889373779},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5789999961853027},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5403000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48240000009536743},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4009000062942505},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2610.00360","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00360","pdf_url":"https://arxiv.org/pdf/2610.00360","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.00360","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00360","pdf_url":"https://arxiv.org/pdf/2610.00360","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7219155352.pdf","grobid_xml":"https://content.openalex.org/works/W7219155352.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2736601468","https://openalex.org/W2895279298","https://openalex.org/W4281784898","https://openalex.org/W4391631327","https://openalex.org/W4402754209","https://openalex.org/W4417307793","https://openalex.org/W7127399381","https://openalex.org/W7133219990"],"related_works":["https://openalex.org/W7164031941","https://openalex.org/W7155474091","https://openalex.org/W7221102947","https://openalex.org/W4385403828","https://openalex.org/W4377866551","https://openalex.org/W2990747716","https://openalex.org/W7135097851","https://openalex.org/W4413925209","https://openalex.org/W7213305879","https://openalex.org/W7081569241"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"for":[3],"dexterous":[4],"manipulation":[5],"must":[6],"discover":[7],"finger-object":[8],"contacts":[9],"and":[10,83,96,106,124,156,204,226],"then":[11],"control":[12,58,173],"the":[13,16,21,27,175,179,192,220],"object":[14],"precisely;":[15],"action":[17,51],"noise":[18,52,172,208],"that":[19,64],"serves":[20],"first":[22],"goal":[23],"can":[24],"interfere":[25],"with":[26,134,161,191],"second.":[28],"In":[29],"trajectory-guided":[30],"settings":[31,85],"such":[32],"as":[33],"ViViDex,":[34],"where":[35],"RL":[36],"refine":[37],"hand-object":[38],"trajectories":[39],"from":[40,73,115,147],"human":[41],"video,":[42],"our":[43],"baseline":[44],"PPO":[45,99,168,181],"runs":[46],"end":[47],"near":[48],"their":[49],"initial":[50],"after":[53],"5M":[54],"steps,":[55,71],"motivating":[56],"explicit":[57,67],"of":[59,69],"exploration":[60,77],"scale.":[61],"DexPolicy":[62],"makes":[63],"scale":[65],"an":[66,135],"function":[68],"training":[70,108],"annealing":[72],"broad":[74],"to":[75,117,121,126,149,153,158,206],"narrow":[76],"while":[78],"holding":[79],"loss,":[80],"architecture,":[81],"reward,":[82],"optimizer":[84,177],"fixed.":[86],"We":[87],"study":[88],"three":[89,107,141,196],"policy-optimization":[90,227],"settings:":[91],"PPO,":[92],"critic-free":[93],"GRPO":[94],"continuation,":[95],"a":[97,130],"flow-parameterized":[98],"variant":[100],"(FPO).":[101],"Across":[102],"five":[103],"YCB":[104],"objects":[105,142],"seeds,":[109],"mean":[110,144,185],"deterministic":[111,201],"Target":[112,145,186,202],"success":[113,146,187,218],"rises":[114],"49.4%":[116],"68.1%":[118],"(FPO),":[119,151],"14.1%":[120],"45.4%":[122],"(GRPO),":[123,155],"32.0%":[125],"35.7%":[127],"(PPO).":[128],"On":[129],"RealMan":[131],"RM75":[132],"arm":[133],"Inspire/RH56":[136],"hand,":[137],"360":[138],"trials":[139],"over":[140,174],"raise":[143],"25.0%":[148],"85.0%":[150],"10.0%":[152],"63.3%":[154],"8.3%":[157],"43.3%":[159],"(PPO),":[160],"one":[162],"trained":[163],"model":[164],"per":[165,224],"object-method":[166],"condition.":[167],"component":[169],"screening":[170],"favors":[171],"tested":[176,197],"contraction;":[178],"selected":[180],"schedule":[182],"yields":[183],"higher":[184],"than":[188],"linear":[189],"decay":[190],"same":[193],"endpoints":[194],"on":[195],"objects.":[198],"Training":[199],"return,":[200],"success,":[203],"tolerance":[205],"execution":[207,222],"dissociate;":[209],"schedules":[210],"should":[211],"therefore":[212],"be":[213],"judged":[214],"by":[215],"terminal":[216],"task":[217,225],"under":[219],"intended":[221],"conditions,":[223],"setting.":[228],"Code:":[229],"https://github.com/AIGeeksGroup/DexPolicy.":[230],"Website:":[231],"https://aigeeksgroup.github.io/DexPolicy.":[232]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-04T00:00:00"}