arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.08320cs.AI
收藏

通过程序归纳解释迁移系统

Explaining Transition Systems through Program Induction

The University of Edinburgh(爱丁堡大学)

Svetlin Penkov, Subramanian Ramamoorthy

摘要:

解释和推理的过程,观察到的黑箱现象的基础,使因果机制的发现,推导出合适的抽象表示和制定更强大的预测。我们建议学习高层次的功能程序,以表示抽象的模型,捕捉不变的结构中观察到的数据。我们介绍的$π$机(程序感应机)-一个架构,能够诱导可解释的LISP类程序从观察到的数据跟踪。我们提出了一个基于反向传播,梯度下降和A* 搜索的程序学习的优化过程。我们将所提出的方法应用到三个问题:动态系统的系统辨识,解释DQN代理的行为和学习演示在人机交互的情况下。我们的实验结果表明,$π$ -机可以有效地诱导可解释的程序从个人的数据痕迹。

英文摘要:

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to learn high level functional programs in order to represent abstract models which capture the invariant structure in the observed data. We introduce the $π$-machine (program-induction machine) -- an architecture able to induce interpretable LISP-like programs from observed data traces. We propose an optimisation procedure for program learning based on backpropagation, gradient descent and A* search. We apply the proposed method to three problems: system identification of dynamical systems, explaining the behaviour of a DQN agent and learning by demonstration in a human-robot interaction scenario. Our experimental results show that the $π$-machine can efficiently induce interpretable programs from individual data traces.

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。

↑