一种基于不确定性的自适应探索新框架
A Novel Framework for Uncertainty-Driven Adaptive Exploration
AI总结：
本文提出了一种基于不确定性的自适应探索框架，通过整合不同不确定性测量机制，提升了在复杂环境中的探索效率和策略性能。
摘要：
自适应探索方法提出了一种交替进行探索与利用的方法来学习复杂的策略。对于此类方法来说，一个重要问题是确定何时切换探索与利用以及反之亦然。这在需要学习长且复杂的动作序列的领域中至关重要。在本工作中，我们提出了一种通用的自适应探索框架，利用不确定性以系统的方式解决这一重要问题。我们的框架将以前的自适应探索方法作为特殊情况包含在内。此外，我们可以在我们的框架中整合任何所选的不确定性测量机制，例如内在动机或基于知识不确定性的探索方法。我们实验表明，我们的框架产生了一种在多个环境中均优于标准方法的自适应探索策略。
英文摘要：
Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and exploitation and vice versa. This is critical in domains that require the learning of long and complex sequences of actions. In this work, we present a generic adaptive exploration framework that employs uncertainty to address this important issue in a principled manner. Our framework includes previous adaptive exploration approaches as special cases. Moreover, we can incorporate in our framework any uncertainty-measuring mechanism of choice, for instance mechanisms used in intrinsic motivation or epistemic uncertainty-based exploration methods. We experimentally demonstrate that our framework gives rise to adaptive exploration strategies that outperform standard ones across several environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
