arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.05340cs.AI
收藏

从游戏到符号推理:学习Alpha(Go)Zero风格的SAT求解器启发式

From Gameplay to Symbolic Reasoning: Learning SAT Solver Heuristics in the Style of Alpha(Go) Zero

Purdue University(普渡大学)

Fei Wang, Tiark Rompf

摘要:

尽管深度神经网络最近在图像和语音识别、自然语言处理和强化学习等各个领域取得了成功,但在将数值优化的力量引入符号推理方面,我们仍然面临着巨大的挑战。研究人员已经提出了不同的途径,例如用于证明合成的神经机器翻译,用于表示符号模式的符号和表达式的矢量化,以及用于降维的神经后端与用于决策的符号前端的耦合。然而,这些初步的探索仍然只是点的解决方案,并承担其他缺点,如缺乏正确性保证。在本文中,我们提出了将符号推理转换为游戏的方法,并在符号问题上直接利用Alpha(Go)Zero风格的深度强化学习的力量。使用布尔可满足性(SAT)问题作为展示,我们证明了我们的方法的可行性,以及模块化,效率和正确性保证的优点。

英文摘要:

Despite the recent successes of deep neural networks in various fields such as image and speech recognition, natural language processing, and reinforcement learning, we still face big challenges in bringing the power of numeric optimization to symbolic reasoning. Researchers have proposed different avenues such as neural machine translation for proof synthesis, vectorization of symbols and expressions for representing symbolic patterns, and coupling of neural back-ends for dimensionality reduction with symbolic front-ends for decision making. However, these initial explorations are still only point solutions, and bear other shortcomings such as lack of correctness guarantees. In this paper, we present our approach of casting symbolic reasoning as games, and directly harnessing the power of deep reinforcement learning in the style of Alpha(Go) Zero on symbolic problems. Using the Boolean Satisfiability (SAT) problem as showcase, we demonstrate the feasibility of our method, and the advantages of modularity, efficiency, and correctness guarantees.

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。

↑