4 papers
Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
Daniel Ebi, Damien Ernst, Klemens Böhm +1
Asymmetric reinforcement learning leverages privileged information available during training to improve learning under partial observability. Existing asymmetric actor-critic metho…
Generalizability of experimental studies
Federico Matteucci, Vadim Arzamasov, Jose Cribeiro-Ramallo +3
Experimental studies are a cornerstone of Machine Learning (ML) research. A common and often implicit assumption is that the study's results will generalize beyond the study itself…
Adversarial Subspace Generation for Outlier Detection in High-Dimensional Data
Jose Cribeiro-Ramallo, Federico Matteucci, Paul Enciu +4
Outlier detection in high-dimensional tabular data is challenging since data is often distributed across multiple lower-dimensional subspaces -- a phenomenon known as the Multiple…
Partial-Label Learning with a Reject Option
Tobias Fuchs, Florian Kalinke, Klemens Böhm
In real-world applications, one often encounters ambiguously labeled data, where different annotators assign conflicting class labels. Partial-label learning allows training classi…