XDQN：通过模仿可解释的固有DQN
XDQN: Inherently Interpretable DQN through Mimicking
摘要：
虽然深度强化学习（DRL）方法已成功应用于具有挑战性的任务，但其在现实世界操作环境中的应用受到方法提供解释的有限能力的挑战。在DRL的可解释性的范例是可解释的盒子设计范例，其中可解释的模型取代DRL方法的内部组成模型，从而使DRL方法“内在”可解释。在本文中，我们探讨了这种范式，我们提出了XDQN，DQN的一个可解释的变体，它使用了一个通过模仿训练的可解释的策略模型。XDQN在一个复杂的，现实世界的操作多智能体问题，其中代理是独立的学习者解决拥塞问题的挑战。具体而言，XDQN评估在三个MARL的情况下，有关的需求容量平衡问题的空中交通管理。XDQN实现了类似于DQN的性能，同时证明了它提供全局模型解释和局部决策解释的能力。
英文摘要：
Although deep reinforcement learning (DRL) methods have been successfully applied in challenging tasks, their application in real-world operational settings is challenged by methods' limited ability to provide explanations. Among the paradigms for explainability in DRL is the interpretable box design paradigm, where interpretable models substitute inner constituent models of the DRL method, thus making the DRL method "inherently" interpretable. In this paper we explore this paradigm and we propose XDQN, an explainable variation of DQN, which uses an interpretable policy model trained through mimicking. XDQN is challenged in a complex, real-world operational multi-agent problem, where agents are independent learners solving congestion problems. Specifically, XDQN is evaluated in three MARL scenarios, pertaining to the demand-capacity balancing problem of air traffic management. XDQN achieves performance similar to that of DQN, while its abilities to provide global models' interpretations and interpretations of local decisions are demonstrated.
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。
