arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.00489cs.LG
收藏

具有动态因果关系的可解释模仿学习

Interpretable Imitation Learning with Dynamic Causal Relations

The Pennsylvania State University(宾夕法尼亚州立大学);NEC Laboratories America(NEC美国实验室);East China Normal University(华东师范大学)

Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen

AI总结:

针对模仿学习智能体黑箱难解释、决策因果机制动态变化的问题,提出基于格兰杰因果的可自解释模仿学习框架,以状态依赖的动态因果图揭示决策逻辑,在多数据集上兼顾可解释性与预测准确率。

摘要:

模仿学习通过模仿专家演示来学习智能体策略,已在医疗方案、自动驾驶等诸多应用中展现出可观成效。然而,解释智能体习得的控制策略仍是一项难题,困难主要源于两方面:其一,模仿学习中的智能体通常以深度神经网络实现,这类模型属于黑箱模型,缺乏可解释性;其二,智能体决策背后的潜在因果机制可能沿轨迹变化,而非在所有时间步保持静态。\n为提升神经智能体的透明度与可解释性,我们提出以有向无环因果图的形式呈现其习得的知识,图中节点为动作与状态变量,边表示预测背后的因果关系。此外,我们将该因果发现过程设计为状态依赖的,使其能够对潜在因果图中的动态性建模。具体而言,我们从Granger因果(格兰杰因果)的视角开展因果发现,提出了一种可自解释的模仿学习框架{\textbackslash method}。该框架由动态因果发现模块、因果编码模块和预测模块三部分组成,采用端到端方式训练。模型训练完成后,我们可获取其决策背后状态与动作变量之间的因果关系,从而揭示其习得的策略。\n在合成数据集与真实世界数据集上的实验结果表明,所提出的{\textbackslash method}在学习动态因果图以理解模仿学习决策过程的同时,还能保持较高的预测准确率,验证了其有效性。

英文摘要:

Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret control policies learned by the agent. Difficulties mainly come from two aspects: 1) agents in imitation learning are usually implemented as deep neural networks, which are black-box models and lack interpretability; 2) the latent causal mechanism behind agents' decisions may vary along the trajectory, rather than staying static throughout time steps. To increase transparency and offer better interpretability of the neural agent, we propose to expose its captured knowledge in the form of a directed acyclic causal graph, with nodes being action and state variables and edges denoting the causal relations behind predictions. Furthermore, we design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. Concretely, we conduct causal discovery from the perspective of Granger causality and propose a self-explainable imitation learning framework, {\method}. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner. After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed {\method} in learning the dynamic causal graphs for understanding the decision-making of imitation learning meanwhile maintaining high prediction accuracy.

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。

↑