State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment collect millions of observations. This makes it hard transfer success industrial control problems, where simulations are often very costly or do not exist, and exploring in the real can potentially lead catastrophic events. Recently developed, model-free, offline RL algori...

Abstract Meta-analysis, the statistical analysis of results from separate studies, is a fundamental building block science. But assumptions classical meta-analysis models are not satisfied whenever publication bias present, which causes inconsistent parameter estimates. Hedges’ selection function model takes into account, but estimating and inferring with this tough for some datasets. Using gen...