加权记分贝叶斯多臂老虎机算法：通过重复曝光优化解决计算难题（英文版）

英文标题：Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality中文摘要：研究了一个权重计数的赌博算法，其中动作损失与最近 $m$ 个时间步骤中该动作被播放的次数的加权求和有关，并引入了 “重复暴露最优性” 的条件来最小化完备策略遗憾，提出了简单的修改后的连续消除算法，并对其进行了理论和实验分析。英文摘要：In recommender system or crowdsourcing applications of online learning, ahuman's preferences or abilities are often a function of the algorithm's recentactions. Motivated by this, a significant line of work has formalized settingswhere an action's loss is a function of the number of tim