xGAIL: Explainable Generative Adversarial Imitation Learning for Explainable Human Decision Analysis
xGAIL: Explainable Generative Adversarial Imitation Learning for Explainable Human Decision Analysis
复制标题
DOI：
10.1145/3394486.3403186
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Menghai Pan;Weixiao Huang;Yanhua Li;Xun Zhou;Jun Luo
中科院分区：
文献类型：
--
作者：
Menghai Pan;Weixiao Huang;Yanhua Li;Xun Zhou;Jun Luo
为了做出日常决策，人类代理设计了他们自己的“策略”来管理他们的移动动态（例如，出租车司机有首选的工作区域和时间，城市通勤者有首选的路线和交通方式）。最近的研究，如生成对抗模仿学习（GAIL），证明了使用深度神经网络（DNN）从人类行为数据中学习人类决策策略的成功，DNN可以准确地模仿人类在各种场景中的行为，例如，然而，这种基于DNN的模型本质上是“黑盒”模型，使得很难解释模型从人类那里学到了什么知识，以及模型如何做出这样的决定，这在模仿学习的文献中没有得到解决。本文通过提出xGAIL来解决这一研究空白，xGAIL是第一个可解释的生成对抗模仿学习框架。拟议的xGAIL框架由两个新的组件组成，包括空间激活最大化（SpatialAM）和空间随机输入采样解释（SpatialRISE），从经过良好训练的GAIL模型中提取全局和局部知识，解释人类代理如何做出决策。特别是，我们以出租车司机的寻车策略为例，验证了所提出的xGAIL框架的有效性。我们对大规模真实世界出租车轨迹数据的分析从两个方面显示了有希望的结果：i）关于附近交通状况促使出租车司机选择特定方向寻找下一个乘客的全局可解释知识，以及ii）出租车司机在做出特定决策时考虑的关键（有时隐藏）因素的局部可解释知识。
To make daily decisions, human agents devise their own "strategies" governing their mobility dynamics (e.g., taxi drivers have preferred working regions and times, and urban commuters have preferred routes and transit modes). Recent research such as generative adversarial imitation learning (GAIL) demonstrates successes in learning human decision-making strategies from their behavior data using deep neural networks (DNNs), which can accurately mimic how humans behave in various scenarios, e.g., playing video games, etc. However, such DNN-based models are "black box" models in nature, making it hard to explain what knowledge the models have learned from human, and how the models make such decisions, which was not addressed in the literature of imitation learning. This paper addresses this research gap by proposing xGAIL, the first explainable generative adversarial imitation learning framework. The proposed xGAIL framework consists of two novel components, including Spatial Activation Maximization (SpatialAM) and Spatial Randomized Input Sampling Explanation (SpatialRISE), to extract both global and local knowledge from a well-trained GAIL model that explains how a human agent makes decisions. Especially, we take taxi drivers' passenger-seeking strategy as an example to validate the effectiveness of the proposed xGAIL framework. Our analysis on a large-scale real-world taxi trajectory data shows promising results from two aspects: i) global explainable knowledge of what nearby traffic condition impels a taxi driver to choose a particular direction to find the next passenger, and ii) local explainable knowledge of what key (sometimes hidden) factors a taxi driver considers when making a particular decision.