Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning
This work addresses the need for efficient heuristic functions in classical planning, offering a significant speed-up for researchers and practitioners in AI planning, though it is incremental as it builds on existing neural network heuristics.
The paper tackles the problem of learning neural network heuristic functions for classical planning by introducing the Regression based Supervised Learning (RSL) algorithm, which uses regression to select states and formulates a supervised learning problem, resulting in outperforming previous methods in coverage with two orders of magnitude less training time.
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.