{"id":"https://openalex.org/W7135032753","doi":"https://doi.org/10.48550/arxiv.2603.10980","title":"PPGuide: Steering Diffusion Policies with Performance Predictive Guidance","display_name":"PPGuide: Steering Diffusion Policies with Performance Predictive Guidance","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135032753","doi":"https://doi.org/10.48550/arxiv.2603.10980"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10980","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10980","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.10980","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128919990","display_name":"Zixing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zixing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jha, Devesh K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056336556","display_name":"Ahmed H. Qureshi","orcid":"https://orcid.org/0000-0003-2104-2333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qureshi, Ahmed H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062272788","display_name":"Diego Romeres","orcid":"https://orcid.org/0000-0002-8603-2438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romeres, Diego","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":0.48579999804496765,"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":0.48579999804496765,"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":0.45719999074935913,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.007699999958276749,"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/set","display_name":"Set (abstract data type)","score":0.5852000117301941},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5450999736785889},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.460999995470047},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4535999894142151},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.4101000130176544},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.3702000081539154},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3617999851703644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5820000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5547000169754028},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10980","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10980","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10980","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10980","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"policies":[1],"have":[2],"shown":[3],"to":[4,30,89,101,123],"be":[5,49],"very":[6],"efficient":[7],"at":[8,72],"learning":[9,43,88],"complex,":[10],"multi-modal":[11],"behaviors":[12],"for":[13],"robotic":[14],"manipulation.":[15],"However,":[16],"errors":[17],"in":[18,151],"generated":[19],"action":[20],"sequences":[21],"can":[22,27],"compound":[23],"over":[24],"time":[25],"which":[26,47,92],"potentially":[28],"lead":[29],"failure.":[31,104],"Some":[32],"approaches":[33],"mitigate":[34],"this":[35,112,117],"by":[36],"augmenting":[37],"datasets":[38],"with":[39],"expert":[40],"demonstrations":[41],"or":[42,103],"predictive":[44],"world":[45],"models":[46],"might":[48],"computationally":[50],"expensive.":[51],"We":[52,105,131],"introduce":[53],"Performance":[54],"Predictive":[55],"Guidance":[56],"(PPGuide),":[57],"a":[58,64,79,108,120,137],"lightweight,":[59],"classifier-based":[60],"framework":[61],"that":[62],"steers":[63],"pre-trained":[65],"diffusion":[66],"policy":[67,126],"away":[68],"from":[69,95,142],"failure":[70],"modes":[71],"inference":[73],"time.":[74],"PPGuide":[75,135],"makes":[76],"use":[77],"of":[78,140],"novel":[80],"self-supervised":[81],"process:":[82],"it":[83],"uses":[84],"attention-based":[85],"multiple":[86],"instance":[87],"automatically":[90],"estimate":[91],"observation-action":[93],"chunks":[94],"the":[96,125,143],"policy's":[97],"rollouts":[98],"are":[99],"relevant":[100],"success":[102],"then":[106],"train":[107],"performance":[109],"predictor":[110,118],"on":[111],"self-labeled":[113],"data.":[114],"During":[115],"inference,":[116],"provides":[119],"real-time":[121],"gradient":[122],"guide":[124],"toward":[127],"more":[128],"robust":[129],"actions.":[130],"validated":[132],"our":[133],"proposed":[134],"across":[136],"diverse":[138],"set":[139],"tasks":[141],"Robomimic":[144],"and":[145],"MimicGen":[146],"benchmarks,":[147],"demonstrating":[148],"consistent":[149],"improvements":[150],"performance.":[152]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-13T00:00:00"}