The development of AlphaZero was a breakthrough in search-based reinforcement learning, by employing a given world model in a Monte-Carlo tree search (MCTS) algorithm to incrementally learn both an action policy and a value estimation. When extending this paradigm to the setting of simultaneous move games we find that the selection strategy of AlphaZero has theoretical shortcomings, including that convergence to a Nash equilibrium is not guaranteed. By analyzing these shortcomings, we find that the selection strategy corresponds to an approximated version of bandit linear optimization using Tsallis entropy regularization with α parameter set to zero, which is equivalent to log-barrier regularization. This observation allows us to refine the search method used by AlphaZero to obtain an algorithm that has theoretically optimal regret as well as superior empirical performance on our evaluation benchmark.

<b><i>Background:</i></b> Statins are progressively accepted as being associated with reduced mortality. However, few real-world statin studies have been conducted on statin use in older people and especially the most frail, that is, the nursing home residents. <b><i>Objective:</i></b> The aim of this study was to evaluate the impact of statin intake in nursing home residents on all-cause mortality. <b><i>Method:</i></b> This is a cross-sectional study of 1,094 older people residing in 6 nursing homes in Flanders (Belgium) between March 1, 2020 and May 30, 2020. We considered all residents who were taking statins for at least 5 days as statin users. All-cause mortality during the 3 months of data collection was the primary outcome. Propensity score overlap-weighted logistic regression models were applied with age, sex, functional status, diabetes, and cardiac failure/ischemia as potential confounders. <b><i>Results:</i></b> 185 out of 1,094 residents were on statin therapy (17%). The statin intake was associated with decreased all-cause mortality: 4% absolute risk reduction; adjusted odds ratio 0.50; CI 0.31–0.81, <i>p</i> = 0.005. <b><i>Conclusions:</i></b> The statin intake was associated with decreased all-cause mortality in older people residing in nursing homes. More in-depth studies investigating the potential geroprotector effect of statins in this population are needed.

Edit rules are simple tuple-level constraints that concisely model which tuples are not permitted in a consistent relation. Previously, developed algorithms mostly assumed nominal data. This implies that ordinal data either had to be discarded or discretized according to expert knowledge. We can omit this by working with the ordinal data directly. In this paper we explore the discovery of low lift pairwise ordinal edit rules and propose an efficient algorithm employing several pruning strategies derived from the lift measure. Our experiments show that we can obtain a similar precision as nominal algorithms, while having an acceptable computational cost.

No abstract

No abstract