Howevb isnon-zero Similarlyr(s, ) are features: r(s, a)= (s, a)>w. Assumption A3(Featureexcitation)Forapolicy withstationarydistributiond (s, a), define =E(s,a) d [ (s, a) (s, a)>].

In this paper, we introduce a new class of structured matrices, which unifies and generalizes structured classes from previous works.

Neural Information Processing Systems http://nips.cc/

One of the core problems of modern statistics and machine learning is to approximate difficultto-compute probability distributions.

Reinforcement learning (RL) algorithms often require a large number of data samples to learn a control policy. As a result, training them directly on the real-world systems is expensive and potentially dangerous.

( , 0)

This workproposesMaskTune, a masking strategy that prevents over-reliance on spurious (or a limited number of) features. MaskTuneforces the trained model to explore new features during asingleepochfinetuning bymasking previously discoveredfeatures.MaskTune, unlike earlier approaches for mitigating shortcut learning, does not require any supervision, suchasannotating spurious features orlabels forsubgroup samples in a dataset.

Theorem 1.Consider Algorithm 1 with, 1/L, k = krˆq(vk, k)k 2, and >0. Suppose that Assumptions 1, 2, and 3 hold.