Recent years saw a plethora of work on explaining complex intelligent agents. One example is the development of several algorithms that generate saliency maps which show how much each pixel attributed to the agents' decision. However, most evaluations of such saliency maps focus on image classification tasks. As far as we know, there is no work which thoroughly compares different saliency maps for Deep Reinforcement Learning agents. This paper compares four perturbation-based approaches to create saliency maps for Deep Reinforcement Learning agents trained on four different Atari 2600 games. All four approaches work by perturbing parts of the input and measuring how much this affects the agent's output. The approaches are compared using three computational metrics: dependence on the learned parameters of the agent (sanity checks), faithfulness to the agent's reasoning (input degradation), and run-time.

中文翻译：

---

对基于摄动的显着性图进行基准测试，以解释深度强化学习代理

近年来，在解释复杂智能代理方面进行了大量工作。一个示例是开发几种生成显着性图的算法，这些显着性图显示每个像素归因于代理决策的程度。但是，此类显着性图的大多数评估都集中在图像分类任务上。据我们所知，尚无任何工作可以对“深度强化学习”代理的不同显着性图进行彻底比较。本文比较了四种基于扰动的方法来为在四种不同的Atari 2600游戏中训练的深度强化学习代理创建显着性图。这四种方法都是通过扰动部分输入并测量这对代理的输出有多大影响来工作的。使用三种计算指标对这些方法进行比较：依赖于代理的学习参数（合理性检查），