{"id":"https://openalex.org/W7214744378","doi":"https://doi.org/10.48550/arxiv.2609.35690","title":"Agent Priors-guided Policy Learning","display_name":"Agent Priors-guided Policy Learning","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214744378","doi":"https://doi.org/10.48550/arxiv.2609.35690"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35690","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35690","pdf_url":"https://arxiv.org/pdf/2609.35690","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2609.35690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126011711","display_name":"Puming (Oscar) Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiang, Puming","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101742191","display_name":"Tao Hu","orcid":"https://orcid.org/0000-0002-1382-7213","observed_orcids":["https://orcid.org/0000-0002-1382-7213"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hu, Tianrun","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060916770","display_name":"Haozhe Du","orcid":"https://orcid.org/0000-0002-9431-7572","observed_orcids":["https://orcid.org/0000-0002-9431-7572"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Du, Haozhe","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153455713","display_name":"Yibo Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li, Yibo","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151735311","display_name":"Zhiwei Xue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xue, Zhiwei","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153456349","display_name":"Xinhu Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li, Xinhu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066073375","display_name":"Harold Soh","orcid":"https://orcid.org/0000-0002-3278-0035","observed_orcids":["https://orcid.org/0000-0002-3278-0035"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Soh, Harold","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.7538999915122986,"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":0.7538999915122986,"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":0.24060000479221344,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0019000000320374966,"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/compositional-generalization","display_name":"compositional generalization","score":0.781000018119812},{"id":"https://openalex.org/keywords/skill-generalization","display_name":"skill generalization","score":0.968999981880188},{"id":"https://openalex.org/keywords/structural-priors","display_name":"structural priors","score":0.8259999752044678},{"id":"https://openalex.org/keywords/skill-composition","display_name":"skill composition","score":0.7070000171661377},{"id":"https://openalex.org/keywords/robot-policy-learning","display_name":"robot policy learning","score":0.5450000166893005},{"id":"https://openalex.org/keywords/construction-agents","display_name":"construction agents","score":0.5509999990463257},{"id":"https://openalex.org/keywords/meta-world","display_name":"Meta-World","score":0.4819999933242798},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8118000030517578},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6786999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291000247001648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4494999945163727},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2603999972343445}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35690","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35690","pdf_url":"https://arxiv.org/pdf/2609.35690","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.35690","doi":"https://doi.org/10.48550/arxiv.2609.35690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35690","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.35690","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35690","pdf_url":"https://arxiv.org/pdf/2609.35690","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W7214744378.pdf","grobid_xml":"https://content.openalex.org/works/W7214744378.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2109910161","https://openalex.org/W2787066086","https://openalex.org/W3001865277","https://openalex.org/W3134487742","https://openalex.org/W4221167441","https://openalex.org/W4224912544","https://openalex.org/W4225873172","https://openalex.org/W4380558462","https://openalex.org/W4382202844","https://openalex.org/W4383109252","https://openalex.org/W4385403811","https://openalex.org/W4387839203","https://openalex.org/W4388660746","https://openalex.org/W4402354036","https://openalex.org/W4402354101","https://openalex.org/W4407719611","https://openalex.org/W4413924995","https://openalex.org/W4414359710","https://openalex.org/W4414818182","https://openalex.org/W4416377103","https://openalex.org/W4417011634","https://openalex.org/W7110887972","https://openalex.org/W7134946402","https://openalex.org/W7135197322","https://openalex.org/W7162039799","https://openalex.org/W7165356838","https://openalex.org/W7166746312","https://openalex.org/W7167682355","https://openalex.org/W7169837528","https://openalex.org/W7202187155","https://openalex.org/W7203705067","https://openalex.org/W7203787083"],"related_works":["https://openalex.org/W7162039799","https://openalex.org/W7020603003","https://openalex.org/W4285165559","https://openalex.org/W7213321597","https://openalex.org/W4221158790","https://openalex.org/W2276692341","https://openalex.org/W7133225416","https://openalex.org/W2736337778","https://openalex.org/W2945794705","https://openalex.org/W7021151172"],"abstract_inverted_index":{"Robots":[0],"that":[1,86,121],"learn":[2],"from":[3],"a":[4,53,73,78,83,115,122,240],"few":[5],"demonstrations":[6,168],"often":[7],"require":[8],"two":[9,36],"forms":[10],"of":[11,102,235],"generalization.":[12],"Compositional":[13],"generalization":[14,23,216],"recombines":[15],"skills":[16,49],"to":[17,94,131],"solve":[18],"new":[19,33,200],"tasks,":[20,211],"and":[21,47,107,179,181,196,208,217,245],"skill":[22,30,54,70,215,221,243,246],"lets":[24],"the":[25,48,59,69,103,108,127,132,140,150,224,233],"learned":[26],"policy":[27,62,141,151,184],"behind":[28],"each":[29,39,96,177],"work":[31],"in":[32,144,157],"situations.":[34],"The":[35],"depend":[37],"on":[38,126],"other,":[40],"yet":[41],"information":[42,226],"is":[43,56,63,93],"lost":[44],"between":[45,105,242],"composition":[46,67,106,148],"it":[50,137,146],"calls.":[51],"Where":[52],"works":[55],"determined":[57],"by":[58],"structure":[60],"its":[61],"trained":[64],"with,":[65],"while":[66],"sees":[68],"only":[71,125],"through":[72],"separate":[74],"description,":[75],"such":[76],"as":[77,100,239],"name,":[79],"an":[80],"instruction,":[81],"or":[82],"symbolic":[84],"operator,":[85],"omits":[87],"this":[88,155],"structure.":[89],"Our":[90],"key":[91],"idea":[92,156],"use":[95,234],"policy's":[97],"structural":[98,111,174,237],"prior":[99,112],"part":[101],"interface":[104,225],"skill.":[109],"A":[110,163,187],"states":[113],"what":[114],"behavior":[116],"depends":[117,124],"on,":[118],"for":[119,176],"example":[120],"grasp":[123],"gripper's":[128],"pose":[129],"relative":[130],"object.":[133],"Built":[134],"into":[135,169],"training,":[136],"shapes":[138],"where":[139,149],"generalizes;":[142],"stated":[143],"language,":[145],"tells":[147],"applies.":[152],"We":[153],"instantiate":[154],"Agent":[158],"Priors-guided":[159],"Policy":[160],"Learning":[161],"(APPL).":[162],"construction":[164],"agent":[165,189],"segments":[166],"complete":[167],"reusable":[170],"skills,":[171],"proposes":[172],"several":[173],"priors":[175],"skill,":[178],"trains":[180],"verifies":[182],"one":[183],"per":[185],"prior.":[186],"runtime":[188],"then":[190],"selects":[191],"among":[192],"these":[193],"prior-specific":[194],"policies":[195],"composes":[197],"them":[198],"toward":[199],"task":[201],"goals":[202],"using":[203],"their":[204],"interfaces.":[205],"Across":[206],"MetaWorld":[207],"long-horizon":[209],"ManiSkill":[210],"APPL":[212],"improves":[213],"out-of-distribution":[214],"enables":[218],"previously":[219],"unseen":[220],"compositions;":[222],"ablating":[223],"substantially":[227],"reduces":[228],"performance.":[229],"These":[230],"results":[231],"support":[232],"training-time":[236],"assumptions":[238],"bridge":[241],"learning":[244],"composition.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}