{"id":"https://openalex.org/W7130367226","doi":"https://doi.org/10.48550/arxiv.2602.15206","title":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","display_name":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7130367226","doi":"https://doi.org/10.48550/arxiv.2602.15206"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.15206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15206","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.15206","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126285337","display_name":"Rapha\u00ebl Baur","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Baur, Rapha\u00ebl","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075901884","display_name":"Yannick Metz","orcid":"https://orcid.org/0000-0001-5955-4487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Metz, Yannick","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126344639","display_name":"Maria Gkoulta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gkoulta, Maria","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126357388","display_name":"Mennatallah El-Assady","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"El-Assady, Mennatallah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048076721","display_name":"Giorgia Ramponi","orcid":"https://orcid.org/0000-0002-3076-5448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramponi, Giorgia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026228535","display_name":"Thomas Kleine Buening","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buening, Thomas Kleine","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126285337"],"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.41350001096725464,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.41350001096725464,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12049999833106995,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10649999976158142,"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/inference","display_name":"Inference","score":0.7290999889373779},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.578499972820282},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5461000204086304},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.545199990272522},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5443999767303467},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5085999965667725},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.448199987411499},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4374000132083893},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7290999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009000182151794},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.578499972820282},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.545199990272522},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.15206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15206","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.15206","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15206","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":"article"},"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":{"Reward":[0],"learning":[1,52],"typically":[2],"relies":[3],"on":[4],"a":[5,61,78,86,99,110],"single":[6,100],"feedback":[7,12,31,55,68,108,141,168],"type":[8,69],"or":[9],"combines":[10],"multiple":[11,54],"types":[13,32,56],"using":[14],"manually":[15],"weighted":[16],"loss":[17,120],"terms.":[18],"Currently,":[19],"it":[20],"remains":[21],"unclear":[22],"how":[23],"to":[24,109,150],"jointly":[25,130],"learn":[26],"reward":[27,51,64,88,132,155],"functions":[28],"from":[29,53],"heterogeneous":[30],"such":[33],"as":[34,57],"demonstrations,":[35],"comparisons,":[36],"ratings,":[37],"and":[38,90,94,114,124,143,165],"stops":[39],"that":[40,84,129,146],"provide":[41],"qualitatively":[42],"different":[43],"signals.":[44],"We":[45,76],"address":[46],"this":[47],"challenge":[48],"by":[49,97],"formulating":[50],"Bayesian":[58],"inference":[59,82],"over":[60],"shared":[62,87],"latent":[63],"function,":[65],"where":[66],"each":[67],"contributes":[70],"information":[71,139],"through":[72],"an":[73],"explicit":[74],"likelihood.":[75],"introduce":[77],"scalable":[79],"amortized":[80],"variational":[81],"approach":[83,105],"learns":[85],"encoder":[89],"feedback-specific":[91],"likelihood":[92],"decoders":[93],"is":[95],"trained":[96],"optimizing":[98],"evidence":[101],"lower":[102],"bound.":[103],"Our":[104],"avoids":[106],"reducing":[107],"common":[111],"intermediate":[112],"representation":[113],"eliminates":[115],"the":[116],"need":[117],"for":[118,161],"manual":[119],"balancing.":[121],"Across":[122],"discrete":[123],"continuous-control":[125],"benchmarks,":[126],"we":[127],"show":[128],"inferred":[131,154],"posteriors":[133],"outperform":[134],"single-type":[135],"baselines,":[136],"exploit":[137],"complementary":[138],"across":[140,167],"types,":[142],"yield":[144],"policies":[145],"are":[147],"more":[148],"robust":[149],"environment":[151],"perturbations.":[152],"The":[153],"uncertainty":[156],"further":[157],"provides":[158],"interpretable":[159],"signals":[160],"analyzing":[162],"model":[163],"confidence":[164],"consistency":[166],"types.":[169]},"counts_by_year":[],"updated_date":"2026-02-19T06:31:58.851227","created_date":"2026-02-19T00:00:00"}