{"id":"https://openalex.org/W7214788641","doi":"https://doi.org/10.48550/arxiv.2609.32634","title":"PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models","display_name":"PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214788641","doi":"https://doi.org/10.48550/arxiv.2609.32634"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32634","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32634","pdf_url":"https://arxiv.org/pdf/2609.32634","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/2609.32634","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039449527","display_name":"Yunpeng Qing","orcid":"https://orcid.org/0000-0001-7376-9847","observed_orcids":["https://orcid.org/0000-0001-7376-9847"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing, Yunpeng","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023910710","display_name":"Yilun Kong","orcid":"https://orcid.org/0009-0004-4761-9764","observed_orcids":["https://orcid.org/0009-0004-4761-9764"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong, Yilun","raw_affiliation_strings":["Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101381290","display_name":"Sixu Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lin, Sixu","raw_affiliation_strings":["CUHK-Shenzhen ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK-Shenzhen ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153407804","display_name":"Ming Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Ming","raw_affiliation_strings":["Shanghai AI Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory ,","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038688931","display_name":"Yiming Fei","orcid":"https://orcid.org/0000-0001-8102-9726","observed_orcids":["https://orcid.org/0000-0001-8102-9726"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei, Yiming","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153405840","display_name":"Shuang Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Luo, Shuang","raw_affiliation_strings":["Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140174437","display_name":"Yixiao Chi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Yixiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140174963","display_name":"Haoming Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu, Haoming","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153434396","display_name":"Jingyuan Liu","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":"Liu, Jingyuan","raw_affiliation_strings":["Fudan University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University ,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152826231","display_name":"Changxu Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei, Changxu","raw_affiliation_strings":["PolyU ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PolyU ,","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111704214","display_name":"Zhi Hou","orcid":"https://orcid.org/0000-0003-2990-505X","observed_orcids":["https://orcid.org/0000-0003-2990-505X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Zhi","raw_affiliation_strings":["ACE Robotics ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACE Robotics ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604564","display_name":"Changqing Zou","orcid":"https://orcid.org/0000-0001-8264-6849","observed_orcids":["https://orcid.org/0000-0001-8264-6849"]},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zou, Changqing","raw_affiliation_strings":["Zhejiang Lab","Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"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":0.8920999765396118,"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":0.8920999765396118,"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":0.10490000247955322,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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-models","display_name":"vision-language-action models","score":0.828000009059906},{"id":"https://openalex.org/keywords/reinforcement-fine-tuning","display_name":"reinforcement fine-tuning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/long-horizon-manipulation","display_name":"long-horizon manipulation","score":0.8259999752044678},{"id":"https://openalex.org/keywords/bimanual-manipulation","display_name":"bimanual manipulation","score":0.828000009059906},{"id":"https://openalex.org/keywords/geometric-distance","display_name":"geometric distance","score":0.421999990940094},{"id":"https://openalex.org/keywords/libero","display_name":"LIBERO","score":0.5929999947547913}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8884000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176999807357788},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48919999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C110521144","wikidata":"https://www.wikidata.org/wiki/Q193460","display_name":"Scalar field","level":2,"score":0.27410000562667847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32634","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32634","pdf_url":"https://arxiv.org/pdf/2609.32634","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.2609.32634","doi":"https://doi.org/10.48550/arxiv.2609.32634","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32634","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:2609.32634","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32634","pdf_url":"https://arxiv.org/pdf/2609.32634","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/W7214788641.pdf","grobid_xml":"https://content.openalex.org/works/W7214788641.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2978455699","https://openalex.org/W4297808394","https://openalex.org/W4302010007","https://openalex.org/W4391631327","https://openalex.org/W4392223343","https://openalex.org/W4399695759","https://openalex.org/W4403364995","https://openalex.org/W4405030195","https://openalex.org/W4414079054","https://openalex.org/W4414581628","https://openalex.org/W4414674749","https://openalex.org/W4414742138","https://openalex.org/W4414742490","https://openalex.org/W4416236772","https://openalex.org/W4417077863","https://openalex.org/W4417097311","https://openalex.org/W4417256425","https://openalex.org/W4417474423","https://openalex.org/W6929480010","https://openalex.org/W7103139230","https://openalex.org/W7106114475","https://openalex.org/W7106319913","https://openalex.org/W7117676596","https://openalex.org/W7133361213","https://openalex.org/W7147005434","https://openalex.org/W7159648611","https://openalex.org/W7161736086","https://openalex.org/W7162670750","https://openalex.org/W7167589576","https://openalex.org/W7168399438","https://openalex.org/W7204808299"],"related_works":["https://openalex.org/W4417087241","https://openalex.org/W7147005434","https://openalex.org/W4417098967","https://openalex.org/W7212019307","https://openalex.org/W7131476132","https://openalex.org/W7161108916","https://openalex.org/W7157012058","https://openalex.org/W7223401323","https://openalex.org/W7106319913","https://openalex.org/W7143342743"],"abstract_inverted_index":{"Reinforcement":[0,84],"Fine-Tuning~(RFT)":[1],"has":[2],"emerged":[3],"as":[4,38,55],"a":[5,89,119],"promising":[6],"paradigm":[7],"for":[8,19,41,63,104,151],"improving":[9],"Vision-Language-Action~(VLA)":[10],"policies,":[11],"yet":[12],"sparse":[13],"task-level":[14],"outcomes":[15],"provide":[16],"limited":[17,61],"credit":[18,78,103,149],"intermediate":[20,32,66],"transitions,":[21],"especially":[22],"in":[23],"long-horizon":[24],"manipulation.":[25],"A":[26,107],"natural":[27],"approach":[28],"is":[29],"to":[30,69],"model":[31],"task":[33,53,71],"progress":[34,54,92,121,145],"and":[35,98,115,132,156,165,183],"use":[36],"it":[37,100],"dense":[39,102,144],"feedback":[40],"policy":[42,105,154,175],"improvement.":[43],"Despite":[44],"their":[45],"architectural":[46],"differences,":[47],"existing":[48],"progress-aware":[49,184],"methods":[50],"commonly":[51],"formulate":[52],"an":[56],"explicit":[57],"scalar":[58],"prediction,":[59],"providing":[60],"structure":[62],"modeling":[64],"how":[65],"observations":[67],"relate":[68],"the":[70,136],"goal,":[72],"which":[73,87],"may":[74],"hinder":[75],"effective":[76],"transition-level":[77],"assignment.":[79],"We":[80],"introduce":[81],"Progress":[82,110],"Field":[83,111],"Learning":[85],"(PF-RL),":[86],"learns":[88],"structured":[90],"goal-conditioned":[91,127],"representation":[93],"over":[94,177],"pretrained":[95],"VLA":[96],"features":[97],"converts":[99],"into":[101,118],"optimization.":[106],"lightweight":[108],"shared":[109],"head":[112],"maps":[113],"current":[114],"goal":[116],"representations":[117],"compact":[120],"space,":[122],"where":[123],"geometric":[124],"distance":[125],"induces":[126],"value,":[128],"while":[129],"complementary":[130],"temporal":[131],"goal-structure":[133],"objectives":[134],"shape":[135],"learned":[137],"geometry.":[138],"Transition-level":[139],"value":[140],"changes":[141],"naturally":[142],"yield":[143],"advantages,":[146],"enabling":[147],"fine-grained":[148],"assignment":[150],"both":[152],"offline":[153],"improvement":[155],"online":[157],"reinforcement":[158,181],"fine-tuning.":[159],"Extensive":[160],"experiments":[161],"on":[162],"LIBERO,":[163],"RoboTwin2.0,":[164],"real-world":[166],"bimanual":[167],"manipulation":[168],"tasks":[169],"show":[170],"that":[171],"PF-RL":[172],"consistently":[173],"improves":[174],"performance":[176],"strong":[178],"supervised":[179],"fine-tuning,":[180,182],"baselines.":[185]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}
