Zero-shot learning leverages semantic representations such asattributes or class prototypes to bridge source and target classes.

The history of learning for control has been an exciting back and forth between twobroad classes ofalgorithms: planning andreinforcement learning.

In this section, we provide an open-ended discussion on how the prior distribution ( i.e., imbalanced

We consider the problem of estimating the mean of a set of vectors, which are stored in a distributed system.

We provide a few error-bound results on its convergence rates. Specially, we prove that theSPIDER-SFO algorithm achieves a gradient computation cost of O min(n1/2 2, 3) to find an -approximate first-order stationary point. In addition, we prove thatSPIDER-SFO nearly matches the algorithmic lower bound for finding stationary point under the gradient Lipschitz assumption in the finite-sum setting.

The different roles of c and P in this lower bound inspire us to design algorithms that estimate costs and transitions separately. Specifically, assuming the knowledge of c and P, we develop a simple but sub-optimal algorithm and another more involved minimax optimal algorithm (up to logarithmic terms). These algorithms combine the ideas of finite-horizon approximation [Chen et al., 2022a], special Bernstein-style bonuses of the MVP algorithm[Zhangetal.,2020],adaptiveconfidencewidening[WeiandLuo,2021],as well as some new techniques such as properly penalizing long-horizon policies. Finally,when c and P are unknown, we develop avariant ofthe MASTER algorithm [Weiand Luo,2021]and integrate the aforementioned ideas into itto achieve O(min{B?S