Showing stat.MLShow all
2 papers · 1 filter
stat.ML2023
Online learning in bandits with predicted context
Yongyi Guo, Ziping Xu, Susan Murphy
We consider the contextual bandit problem where at each time, the agent only has access to a noisy version of the context and the error variance (or an estimator of this variance).…
stat.ML2023
Effect-Invariant Mechanisms for Policy Generalization
Sorawit Saengkyongam, Niklas Pfister, Predrag Klasnja +2
Policy learning is an important component of many real-world learning systems. A major challenge in policy learning is how to adapt efficiently to unseen environments or tasks. Rec…