We consider a restless bandit problem with Gaussian autoregressive arms, where the state of an arm is only observed when it is played and the state-dependent reward is collected. Since arms are only partially observable, a good decision policy needs to account for the fact that information about the state of an arm becomes more and more obsolete while the arm is not being played. Thus, the deci...

PURPOSE To compare the retinal nerve fiber layer (RNFL) defects in early glaucomatous eyes between highly and non-highly myopic eyes. METHODS Sixty-one highly myopic eyes (< -6.0 diopters [D]) of 61 patients and 55 non-highly myopic eyes of 55 patients with early visual field (VF) defects were studied. The angular locations and widths of the RNFL defects were measured from red-free fundus pho...

A competitive analysis for the online and offline optimization problems for a slotted energy harvesting (EH) wireless communication system is studied. The objective is to design online strategies that minimize the competitive rate gap that is defined as the maximum gap between the optimal rates that can be achieved by the offline and online policies over all possible energy arrival profiles. It...

We generalize the classic dynamic single-item search model to multiple items and vector offers for subsets. We first show a computationally feasible way to solve the dynamic optimization problem, and then prove structural results. Although assignment is not generally monotonically increasing in offer value, we show that, in a special case “additive” model, monotonicity holds if costs are submod...

We propose an approach to learning agents for active robotic mapping, where the goal is to map the environment as quickly as possible. The agent learns to map efficiently in simulated environments by receiving rewards corresponding to how fast it constructs an accurate map. In contrast to prior work, this approach learns an exploration policy based on a user-specified prior over environment con...

We consider the problem of learning the functions computing children from parents in a Structural Causal Model once the underlying causal graph has been identified. This is in some sense the second step after causal discovery. Taking a probabilistic approach to estimating these functions, we derive a natural myopic active learning scheme that identifies the intervention which is optimally infor...

Background: To assess the refractive status of cataract patients with extreme myopia and to measure their accommodative capability after monofocal IOL implantation. Design: Prospective non-randomized study conducted at Tianjin Medical University Eye Centre. Participants: 18 patients with 34 extreme myopic eyes (≥-10 Diopter, ≥27mm axial length), and 14 patients with 27 non-myopic eyes that had ...

AIM To describe and compare the corneal endothelial cell density and morphology in young, low and moderate myopic Chinese adults in Malaysian Chinese population. METHODS Non-contact specular microscopy (Topcon SP3000P, Tokyo, Japan) was performed in low (n=78; 21.22±1.51 years) and moderate (n=78; 21.82±1.40 years) myopic subjects. The mean of three consecutive measurements of endothelial cel...

OBJECTIVES To determine the efficacy of refractive correction alone and patching treatment with near activities on amblyopia associated with myopic anisometropia in children aged 4 to less than 14 years. The associations of visual acuity (VA) improvement with age,degree of anisometropia, patching compliance, presence of strabismus, and presence of eccentric fixation were also investigated. ME...

In this paper,we consider the restless bandit problem, which is one of the most well-studied generalizations of the celebrated stochastic multi-armed bandit problem in decision theory. However, it is known be PSPACE-Hard to approximate to any non-trivial factor. Thus the optimality is very difficult to obtain due to its high complexity. A natural method is to obtain the greedy policy considerin...