Goto

Collaborating Authors

 training distribution






StabilizingOff-PolicyQ-LearningviaBootstrapping ErrorReduction

Neural Information Processing Systems

One of the primary drivers of the success of machine learning methods in open-world perception settings, such ascomputer vision [19]and NLP [8],has been the ability ofhigh-capacity function approximators, suchasdeepneuralnetworks,tolearngeneralizable modelsfromlargeamountsof data.






EvaluatingRobustnesstoDatasetShift viaParametricRobustnessSets

Neural Information Processing Systems

These shifts are defined via parametric changes in the causal mechanisms of observed variables, where constraints on parameters yield a "robustness set" of plausible distributions and acorresponding worst-case loss overthe set.