arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.12237cs.AIcs.LG
收藏

概率树中的因果推理算法

Algorithms for Causal Reasoning in Probability Trees

DeepMind(深度思考)

Tim Genewein, Tom McGrath, Grégoire Déletang, Vladimir Mikulik, Miljan Martic, Shane Legg, Pedro A. Ortega

摘要:

概率树是因果生成过程中最简单的模型之一。它们具有清晰的语义,并且-与因果贝叶斯网络不同-它们可以表示特定于上下文的因果依赖关系,这对于因果归纳是必要的。然而,它们很少受到AI和ML社区的关注。在这里,我们提出了具体的算法,因果推理的离散概率树,涵盖了整个因果层次结构(协会,干预和反事实),并操作任意命题和因果事件。我们的工作扩展域的因果推理的一个非常一般的一类离散随机过程。

英文摘要:

Probability trees are one of the simplest models of causal generative processes. They possess clean semantics and -- unlike causal Bayesian networks -- they can represent context-specific causal dependencies, which are necessary for e.g. causal induction. Yet, they have received little attention from the AI and ML community. Here we present concrete algorithms for causal reasoning in discrete probability trees that cover the entire causal hierarchy (association, intervention, and counterfactuals), and operate on arbitrary propositional and causal events. Our work expands the domain of causal reasoning to a very general class of discrete stochastic processes.

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。

↑