论文标题
通过深厚的加强学习积极学习因果结构
Active Learning of Causal Structures with Deep Reinforcement Learning
论文作者
论文摘要
我们研究了从介入数据中学习因果结构的实验设计问题。我们考虑了一个主动的学习设置，在该设置中，实验者决定在每个步骤中的系统中的一个变量中进行干预，并使用干预措施的结果来恢复变量之间的进一步因果关系。目标是充分识别最少数量干预措施的因果结构。我们为实验设计问题提供了第一个基于深入的学习解决方案。在提出的方法中，我们使用图神经网络将输入图嵌入向量中，并将其馈送到另一个神经网络，该神经网络输出了用于在每个步骤中执行干预的变量。这两个网络均通过Q透视算法共同训练。实验结果表明，所提出的方法在相对于以前的工作中恢复因果结构方面取得了竞争性能，同时大大减少了密集图中的执行时间。
We study the problem of experiment design to learn causal structures from interventional data. We consider an active learning setting in which the experimenter decides to intervene on one of the variables in the system in each step and uses the results of the intervention to recover further causal relationships among the variables. The goal is to fully identify the causal structures with minimum number of interventions. We present the first deep reinforcement learning based solution for the problem of experiment design. In the proposed method, we embed input graphs to vectors using a graph neural network and feed them to another neural network which outputs a variable for performing intervention in each step. Both networks are trained jointly via a Q-iteration algorithm. Experimental results show that the proposed method achieves competitive performance in recovering causal structures with respect to previous works, while significantly reducing execution time in dense graphs.
