A Guiding Principle for Causal Decision Problems.
arXiv: Artificial Intelligence(2019)
摘要
We define a Causal Decision Problem as a Decision Problem where the available actions, the family of uncertain events and the set of outcomes are related through the variables of a Causal Graphical Model $mathcal{G}$. A solution criteria based on Pearlu0027s Do-Calculus and the Expected Utility criteria for rational preferences is proposed. The implementation of this criteria leads to an on-line decision making procedure that has been shown to have similar performance to classic Reinforcement Learning algorithms while allowing for a causal model of an environment to be learned. Thus, we aim to provide the theoretical guarantees of the usefulness and optimality of a decision making procedure based on causal information.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络