Goto

Collaborating Authors

 Country





18fee39e2666f43cf44425138bae9def-Paper-Conference.pdf

Neural Information Processing Systems

Although importance sampling (IS) provides a basic principle for OPE, it is ill-posed for the deterministic target policy with continuous actions.







BiasedStochasticFirst

Neural Information Processing Systems

Our lower bound analysis shows that the sample complexities ofBSGD cannot be improved for general convexobjectives and nonconvexobjectivesexcept for smooth nonconvexobjectiveswith Lipschitz continuous gradient estimator.