[RDF data]
Home | Example Publications
PropertyValue
dcterms:bibliographicCitation <http://dblp.uni-trier.de/rec/bibtex/journals/corr/abs-2307-14085>
dc:creator <https://dblp.l3s.de/d2r/resource/authors/Mengdi_Wang>
dc:creator <https://dblp.l3s.de/d2r/resource/authors/Siyu_Chen>
dc:creator <https://dblp.l3s.de/d2r/resource/authors/Zhuoran_Yang>
foaf:homepage <http://dx.doi.org/doi.org%2F10.48550%2FarXiv.2307.14085>
foaf:homepage <https://doi.org/10.48550/arXiv.2307.14085>
dc:identifier DBLP journals/corr/abs-2307-14085 (xsd:string)
dc:identifier DOI doi.org%2F10.48550%2FarXiv.2307.14085 (xsd:string)
dcterms:issued 2023 (xsd:gYear)
swrc:journal <https://dblp.l3s.de/d2r/resource/journals/corr>
rdfs:label Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks. (xsd:string)
foaf:maker <https://dblp.l3s.de/d2r/resource/authors/Mengdi_Wang>
foaf:maker <https://dblp.l3s.de/d2r/resource/authors/Siyu_Chen>
foaf:maker <https://dblp.l3s.de/d2r/resource/authors/Zhuoran_Yang>
owl:sameAs <http://bibsonomy.org/uri/bibtexkey/journals/corr/abs-2307-14085/dblp>
owl:sameAs <http://dblp.rkbexplorer.com/id/journals/corr/abs-2307-14085>
rdfs:seeAlso <http://dblp.uni-trier.de/db/journals/corr/corr2307.html#abs-2307-14085>
rdfs:seeAlso <https://doi.org/10.48550/arXiv.2307.14085>
dc:title Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks. (xsd:string)
dc:type <http://purl.org/dc/dcmitype/Text>
rdf:type swrc:Article
rdf:type foaf:Document
swrc:volume abs/2307.14085 (xsd:string)