Publikation: RLHF-Blender : A Configurable Interactive Interface for Learning from Diverse Human Feedback
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
To use reinforcement learning from human feedback (RLHF) in practical applications, it is crucial to learn reward models from diverse sources of human feedback, and to consider human factors involved in providing feedback of different types. However, systematic study of learning from diverse types of feedback is held back by limited standardized tooling available to researchers. To bridge this gap, we propose RLHF-Blender, a configurable, interactive interface for learning from human feedback. RLHF-Blender provides a modular experimentation framework and implementation that enables researchers to systematically investigate the properties and qualities of human feedback for reward learning. The system facilitates the exploration of various feedback types, including demonstrations, rankings, comparisons, and natural language instructions, as well as studies considering the impact of human factors on their effectiveness. We discuss a set of concrete research opportunities enabled by RLHF-Blender. More information is available at our website.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
METZ, Yannick, David LINDNER, Raphaël BAUR, Daniel A. KEIM, Mennatallah EL-ASSADY, 2023. RLHF-Blender : A Configurable Interactive Interface for Learning from Diverse Human Feedback. Interactive Learning with Implicit Human Feedback (ILHF) Workshop at ICML 2023. Hawaii, 23. Juli 2023 - 29. Juli 2023. In: Interactive Learning with Implicit Human Feedback Workshop at ICML 2023BibTex
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/67538"> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/67538"/> <dc:creator>Baur, Raphaël</dc:creator> <dcterms:abstract>To use reinforcement learning from human feedback (RLHF) in practical applications, it is crucial to learn reward models from diverse sources of human feedback, and to consider human factors involved in providing feedback of different types. However, systematic study of learning from diverse types of feedback is held back by limited standardized tooling available to researchers. To bridge this gap, we propose RLHF-Blender, a configurable, interactive interface for learning from human feedback. RLHF-Blender provides a modular experimentation framework and implementation that enables researchers to systematically investigate the properties and qualities of human feedback for reward learning. The system facilitates the exploration of various feedback types, including demonstrations, rankings, comparisons, and natural language instructions, as well as studies considering the impact of human factors on their effectiveness. We discuss a set of concrete research opportunities enabled by RLHF-Blender. More information is available at our website.</dcterms:abstract> <dcterms:title>RLHF-Blender : A Configurable Interactive Interface for Learning from Diverse Human Feedback</dcterms:title> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <dc:language>eng</dc:language> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:creator>Lindner, David</dc:creator> <dc:contributor>Lindner, David</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:creator>Metz, Yannick</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-08-08T14:26:53Z</dcterms:available> <dc:creator>Keim, Daniel A.</dc:creator> <dc:creator>El-Assady, Mennatallah</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-08-08T14:26:53Z</dc:date> <dc:contributor>Metz, Yannick</dc:contributor> <dcterms:issued>2023</dcterms:issued> <dc:contributor>Baur, Raphaël</dc:contributor> <dc:contributor>Keim, Daniel A.</dc:contributor> </rdf:Description> </rdf:RDF>