{"id":"https://openalex.org/W7215104948","doi":"https://doi.org/10.48550/arxiv.2609.38890","title":"PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning","display_name":"PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215104948","doi":"https://doi.org/10.48550/arxiv.2609.38890"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38890","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38890","pdf_url":"https://arxiv.org/pdf/2609.38890","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/2609.38890","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018108779","display_name":"Yangang Zou","orcid":"https://orcid.org/0000-0003-1892-2153","observed_orcids":["https://orcid.org/0000-0003-1892-2153"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zou, Yangang","raw_affiliation_strings":["School of Data Science , Fudan University","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154259508","display_name":"Jiajun Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Jiajun","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153845580","display_name":"Weitao Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Weitao","raw_affiliation_strings":["Simple AI","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simple AI","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153929100","display_name":"Haibao Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu, Haibao","raw_affiliation_strings":["The University of Hong Kong","Tuojing Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Tuojing Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154071658","display_name":"Bozhou Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Bozhou","raw_affiliation_strings":["School of Data Science , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153904185","display_name":"Jiawei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiawei","raw_affiliation_strings":["Simple AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simple AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074345072","display_name":"Honglong Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Honglong","raw_affiliation_strings":["Simple AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simple AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154267356","display_name":"Minglei Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Minglei","raw_affiliation_strings":["Simple AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simple AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153766282","display_name":"Li Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Li","raw_affiliation_strings":["School of Data Science , Fudan University","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]}],"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":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":0.9980000257492065,"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":0.9980000257492065,"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":0.0015999999595806003,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/vision-language-action-policies","display_name":"vision-language-action policies","score":0.6700000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973000168800354},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6395999789237976},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.6353999972343445},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38890","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38890","pdf_url":"https://arxiv.org/pdf/2609.38890","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.2609.38890","doi":"https://doi.org/10.48550/arxiv.2609.38890","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38890","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38890","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38890","pdf_url":"https://arxiv.org/pdf/2609.38890","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215104948.pdf","grobid_xml":"https://content.openalex.org/works/W7215104948.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2978455699","https://openalex.org/W4391631327","https://openalex.org/W4399695759","https://openalex.org/W4405030195","https://openalex.org/W4414581628","https://openalex.org/W4414587063","https://openalex.org/W4415097172","https://openalex.org/W4415337442","https://openalex.org/W4416453792","https://openalex.org/W4417256425","https://openalex.org/W6929480010","https://openalex.org/W7128694070","https://openalex.org/W7129725900","https://openalex.org/W7138923929","https://openalex.org/W7161154181","https://openalex.org/W7162494674","https://openalex.org/W7165020664","https://openalex.org/W7165655450","https://openalex.org/W7165936402","https://openalex.org/W7171649728","https://openalex.org/W7202145059","https://openalex.org/W7203463189","https://openalex.org/W7203661348","https://openalex.org/W7203936998"],"related_works":["https://openalex.org/W7204891669","https://openalex.org/W7221199531","https://openalex.org/W7222999879","https://openalex.org/W7166852645","https://openalex.org/W7203463189","https://openalex.org/W7215831568","https://openalex.org/W7221763189","https://openalex.org/W7164027124","https://openalex.org/W7203661348","https://openalex.org/W7222984432"],"abstract_inverted_index":{"Outcome-based":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"post-trains":[4],"vision--language--action":[5],"policies":[6],"using":[7],"terminal":[8,73,98],"success":[9,135,196],"signals,":[10],"but":[11],"assigns":[12],"the":[13,34,54,159],"same":[14],"trajectory-level":[15,150],"advantage":[16],"to":[17,57,133,148,158],"every":[18],"action":[19],"chunk.":[20],"A":[21],"failed":[22],"episode":[23],"can":[24,65,90],"thus":[25],"penalize":[26],"useful":[27],"early":[28],"actions":[29],"as":[30,92],"if":[31],"they":[32],"caused":[33],"failure.":[35],"Existing":[36],"approaches":[37],"seek":[38],"finer-grained":[39],"feedback":[40],"through":[41],"learned":[42],"evaluators,":[43],"adding":[44],"task-specific":[45],"supervision":[46],"or":[47],"additional":[48],"model":[49],"training.":[50],"We":[51,106],"explore,":[52],"for":[53,94,102,110,168],"first":[55],"time":[56],"our":[58],"knowledge,":[59],"whether":[60],"physical":[61,88,120],"relations":[62],"across":[63],"trajectories":[64],"provide":[66,100],"action-chunk":[67],"credit":[68,140],"in":[69,145],"embodied":[70],"RL":[71],"from":[72,113],"outcomes":[74,99,128],"alone,":[75],"without":[76],"an":[77],"auxiliary":[78],"evaluator.":[79],"The":[80],"key":[81],"insight":[82],"is":[83],"that":[84,123,142,176],"rollouts":[85],"reaching":[86],"corresponding":[87,130],"situations":[89],"serve":[91],"references":[93],"one":[95],"another:":[96],"their":[97],"evidence":[101,170],"assessing":[103],"local":[104,182],"progress.":[105],"introduce":[107],"Physical":[108],"Relations":[109],"Inferring":[111],"Credit":[112],"Episodes(PRICE),":[114],"with":[115,181],"two":[116],"components:":[117],"(i)":[118],"a":[119,164],"relational":[121],"graph":[122],"pools":[124],"current":[125],"and":[126,137,162,190,200],"historical":[127],"at":[129],"chunk":[131],"boundaries":[132],"estimate":[134],"potentials;":[136],"(ii)":[138],"confidence-gated":[139],"assignment":[141],"uses":[143],"changes":[144,157],"these":[146],"potentials":[147],"refine":[149],"supervision.":[151],"Our":[152],"analysis":[153],"connects":[154],"oracle":[155],"potential":[156],"terminal-success":[160],"objective":[161],"provides":[163],"finite-sample":[165],"directional":[166],"bound":[167],"outcome-independent":[169],"pools.":[171],"Independent":[172],"continuation":[173],"tests":[174],"show":[175],"PRICE's":[177],"retained":[178],"credits":[179],"align":[180],"progress,":[183],"while":[184],"experiments":[185],"on":[186],"LIBERO,":[187],"RoboTwin":[188],"2.0,":[189],"real":[191],"robots":[192],"demonstrate":[193],"improved":[194],"task":[195],"over":[197],"outcome-based":[198],"baselines":[199],"faster":[201],"learning.":[202]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-02T00:00:00"}