Learning heuristic functions for large state spaces Original Research Article

We investigate the use of machine learning to create effective heuristics for search algorithms such as image or heuristic-search planners such as FF. Our method aims to generate a sequence of heuristics from a given weak heuristic image and a set of unsolved training instances using a bootstrapping procedure. The training instances that can be solved using image provide training examples for a learning algorithm that produces a heuristic image that is expected to be stronger than image. If image is so weak that it cannot solve any of the given instances we use random walks backward from the goal state to create a sequence of successively more difficult training instances starting with ones that are guaranteed to be solvable by image. The bootstrap process is then repeated using image in lieu of image until a sufficiently strong heuristic is produced. We test this method on the 24-sliding-tile puzzle, the 35-pancake puzzle, Rubikʼs Cube, and the 20-blocks world. In every case our method produces a heuristic that allows image to solve randomly generated problem instances quickly with solutions close to optimal.