TL;DR通过使用机器学习方法，基于易于计算的特征，我们训练了一个可满足性分类器和运行时模型，并使用这些模型来选择 SAT 求解器的重启策略，实验结果表明，机器学习能有效提高求解器的性能。
Abstract
restart strategies are an important factor in the performance of conflict-driven davis putnam style sat solvers. Selecting a good restart strategy for a problem instance can enhance the performance of a solver. I