论文标题
从前图像中取样以学习古典计划的启发式功能
Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning
论文作者
论文摘要
我们介绍了一种新算法，基于回归的监督学习（RSL），用于每个实例神经网络（NN）为经典计划问题定义的启发式功能。 RSL使用回归来选择与目标不同距离的相关状态集。然后，RSL制定了一个监督的学习问题，以获取定义NN启发式的参数，并使用标记为目标状态的精确或估计距离的选定状态。我们的实验研究表明，在覆盖范围内，RSL的表现优于先前的经典计划NN启发式功能，同时需要少两个数量级的训练时间。
We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for classical planning problems. RSL uses regression to select relevant sets of states at a range of different distances from the goal. RSL then formulates a Supervised Learning problem to obtain the parameters that define the NN heuristic, using the selected states labeled with exact or estimated distances to goal states. Our experimental study shows that RSL outperforms, in terms of coverage, previous classical planning NN heuristics functions while requiring two orders of magnitude less training time.
