{"id":"https://openalex.org/W7166706330","doi":"https://doi.org/10.48550/arxiv.2606.29834","title":"STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning","display_name":"STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166706330","doi":"https://doi.org/10.48550/arxiv.2606.29834"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29834","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29834","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.29834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139692511","display_name":"Zhihao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051535472","display_name":"Qiuyi Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Qiuyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139655504","display_name":"Yitao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139704286","display_name":"Dongming Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Dongming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859536","display_name":"Yixian Zhang","orcid":"https://orcid.org/0000-0001-7408-7397"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yixian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126121933","display_name":"Shuaihang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shuaihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132582789","display_name":"Liangzhi Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Liangzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139637044","display_name":"Tianxing Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tianxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011086655","display_name":"Z Zhangqin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zefang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139681456","display_name":"Kang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139701916","display_name":"Zhen Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036390522","display_name":"Q. Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Quanlu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107877612","display_name":"J. Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jincheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139698137","display_name":"Xiaodan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Xiaodan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139711284","display_name":"Guoliang Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Guoliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139714588","display_name":"Yu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139705678","display_name":"Feng Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139653764","display_name":"Xinlei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043761995","display_name":"C Shijia Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.4016999900341034,"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":0.4016999900341034,"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":0.32429999113082886,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0502999983727932,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5515999794006348},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.478300005197525},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4749000072479248},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.460999995470047},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.42170000076293945},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.3887999951839447},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.35670000314712524},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6008999943733215},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29834","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29834","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.29834","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29834","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"robot":[1],"learning":[2,24],"increasingly":[3],"relies":[4],"on":[5,63],"heterogeneous":[6],"data,":[7],"but":[8],"demonstrations":[9],"and":[10,19,36,124,132,148],"rollouts":[11],"often":[12],"mix":[13],"useful":[14],"progress":[15,33],"with":[16,136],"stalls,":[17,130],"corrections,":[18],"suboptimal":[20],"behavior.":[21],"Effective":[22],"policy":[23,141],"therefore":[25],"requires":[26],"frame-level":[27],"advantages":[28,52],"that":[29,49],"distinguish":[30],"reliable":[31],"local":[32],"from":[34,53],"failures":[35],"regressions.":[37],"We":[38],"propose":[39],"Self-supervised":[40],"Temporal":[41],"Ensemble":[42],"Advantage":[43],"Modeling":[44],"(STEAM),":[45],"a":[46,78,84,88,97],"label-free":[47],"method":[48],"learns":[50],"such":[51],"expert":[54,67],"demonstrations.":[55],"STEAM":[56,100,128,138],"trains":[57],"an":[58],"ensemble":[59,108],"of":[60],"temporal-offset":[61],"predictors":[62],"frame":[64,85],"pairs":[65],"within":[66],"trajectories,":[68],"using":[69],"the":[70,103,107],"normalized":[71],"temporal":[72,91],"offset":[73],"between":[74],"two":[75],"frames":[76],"as":[77],"self-supervised":[79],"signal.":[80],"Each":[81],"predictor":[82],"maps":[83],"pair":[86],"to":[87,109],"distribution":[89],"over":[90,150],"offsets,":[92],"which":[93],"is":[94],"converted":[95],"into":[96],"scalar":[98],"advantage.":[99],"then":[101],"takes":[102],"minimum":[104],"advantage":[105],"across":[106],"score":[110],"mixed-quality":[111],"rollout":[112],"data":[113],"conservatively.":[114],"Across":[115],"real-world":[116],"bimanual":[117],"towel":[118],"folding,":[119],"chip":[120],"checkout,":[121],"cola":[122],"restocking,":[123],"single-arm":[125],"pick-and-place":[126],"tasks,":[127],"identifies":[129],"failures,":[131],"recoveries.":[133],"When":[134],"combined":[135],"CFGRL,":[137],"further":[139],"improves":[140],"success":[142],"rate":[143],"by":[144],"59%,":[145],"54.3%,":[146],"23%":[147],"16.2%":[149],"baselines,":[151],"respectively.":[152]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}