Rehearsal Learning for Avoiding Undesired Future

Tian Qin, Tian-Zuo Wang, Zhi-Hua Zhou

Keywords: decision-making, structural rehearsal model, Bayesian inference, probabilistic graphical model

TL;DR: We present a rehearsal learning framework based on structural rehearsal models and Bayesian inference for recommending appropriate decisions to avoid undesired future outcomes.

Abstract: Machine learning (ML) models have been widely used to make predictions. Instead of a predictive statement about future outcomes, in many situations we want to pursue a decision: what can we do to avoid the undesired future if an ML model predicts so? In this paper, we present a rehearsal learning framework, in which decisions that can persuasively avoid the happening of undesired outcomes can be found and recommended. Based on the influence relation, we characterize the generative process of variables with structural rehearsal models, consisting of a probabilistic graphical model called rehearsal graphs and structural equations, and find actionable decisions that can alter the outcome by reasoning under a Bayesian framework. Moreover, we present a probably approximately correct bound to quantify the associated risk of a decision. Experiments validate the effectiveness of the proposed rehearsal learning framework and the informativeness of the bound.

Submission Number: 907