We study a novel variant of online finite-horizon Markov Decision Processes with adversarially changing loss functions and initially unknown dynamics. In each episode, the learner suffers the loss accumulated along the trajectory realized by the policy chosen for the episode, and observes aggregate bandit feedback: the trajectory is revealed along with the cumulative loss suffered, rather than the individual losses encountered along the trajectory. Our main result is a computationally efficient algorithm with $O(\sqrt{K})$ regret for this setting, where $K$ is the number of episodes. We establish this result via an efficient reduction to a novel bandit learning setting we call Distorted Linear Bandits (DLB), which is a variant of bandit linear optimization where actions chosen by the learner are adversarially distorted before they are committed. We then develop a computationally-efficient online algorithm for DLB for which we prove an $O(\sqrt{T})$ regret bound, where $T$ is the number of time steps. Our algorithm is based on online mirror descent with a self-concordant barrier regularization that employs a novel increasing learning rate schedule.
翻译:我们研究了一个新型的在线限制-Horizon Markov 决策程序变式, 其损失功能和最初未知的动态发生对抗性变化。 在每集中, 学习者都遭受了按照为该集选政策所选政策所实现的轨迹所积累的损失, 并观察了集体土匪反馈: 轨迹与累积损失一起被揭示, 而不是在轨迹中遇到的个人损失。 我们的主要结果就是在这个环境里, 以$O( sqrt{K}) 来计算高效的算法, 以$O( sqrt{K}) 来表示遗憾, 以美元作为事件的数量。 我们通过高效减少新颖的土匪学习设置来建立这一结果。 我们的算法是以自译自审的屏障校正, 采用新的学习进度表。