This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm, least-squares iteration (RLSVI). Our $\tilde{\mathrm{O}}(H^2S\sqrt{AT})$ high-probability worst-case bound improves the previous sharpest bounds for RLSVI and...

This paper presents two adaptive ECMS schemes which compared to the standard ECMS formulation are extended by an online learning algorithm based on the so-called regret minimization paradigm. While in the first approach the Shrinking Dartboard algorithm is applied to tune the parameter values of the ECMS adaptation rule, in the second approach the Weighted Fractional algorithm averages the resu...

Preface In this thesis I present the result of my investigation into regret minimization for Monte-Carlo Tree Search. The thesis presents the motivation, background, and formal definition of a novel search technique based on minimizing both simple and cumulative regret in a game tree: Hybrid MCTS (H-MCTS). The technique minimizes the two types of regret in a single search-tree. This ensures tha...

Abstract Plastic pollution causing the near-permanent contamination of environment is a preeminent concern. The largest market sector for plastic resins packaging, and food industry plays major role in producing packaging waste. Therefore, gradual switch system towards pro-environmental strategies required to contain waste issue. To this extent, study aimed investigate how consumers relatively ...

Minimization of the rank loss or, equivalently, maximization of the AUC in bipartite ranking calls for minimizing the number of disagreements between pairs of instances. Since the complexity of this problem is inherently quadratic in the number of training examples, it is tempting to ask how much is actually lost by minimizing a simple univariate loss function, as done by standard classificatio...

We consider the problem of rank loss minimization in the setting of multilabel classification, which is usually tackled by means of convex surrogate losses defined on pairs of labels. Very recently, this approach was put into question by a negative result showing that commonly used pairwise surrogate losses, such as exponential and logistic losses, are inconsistent. In this paper, we show a pos...

Objective The aim of this study is to evaluate the menstrual pattern, sexual function, and anxiety, and depression in women with poststerilization regret, and potential influencing factors for regret following TL in Iranian women. MaterialsAndMethods In this cross-sectional study, 166 women with TL were subdivided into two groups including women with poststerilization regret (n=41) and women wi...

In the convex optimization approach to online regret minimization, many methodshave been developed to guarantee a O(√T ) bound on regret for subdifferentiableconvex loss functions with bounded subgradients, by using a reduction to linearloss functions. This suggests that linear loss functions tend to be the hardest onesto learn against, regardless of the underlying d...