论文标题
通过合奏的分配加固学习
Distributional Reinforcement Learning with Ensembles
论文作者
论文摘要
众所周知，合奏方法通常在增强学习中提供增强的性能。在本文中，我们通过在分布强化学习范式中使用小组辅助培训进一步探讨了这一概念。具体而言，我们建议对分类增强学习的扩展，其中分配学习目标是基于合奏收集的总信息。我们从经验上表明，这可能会导致更强大的初始学习，更强的个人绩效水平以及按样本基础上的良好效率。
It is well known that ensemble methods often provide enhanced performance in reinforcement learning. In this paper, we explore this concept further by using group-aided training within the distributional reinforcement learning paradigm. Specifically, we propose an extension to categorical reinforcement learning, where distributional learning targets are implicitly based on the total information gathered by an ensemble. We empirically show that this may lead to much more robust initial learning, a stronger individual performance level, and good efficiency on a per-sample basis.
