Generating A-Star Algorithm Admissible Heuristics Using a Dynamic Dataloader on Neural Networks, Enhanced With Genetic Algorithms, on a Distributed Architecture

Abstract

Heuristic search algorithms are informed search strategies that use heuristics to estimate the minimal cost of the path from the current state to the goal. Using this additional knowledge, this type of algorithms can distinguish non-goal states, and then directs its search towards those that look more promising. This makes these algorithms faster than uninformed search algorithms. The A* algorithm is a well-known example of heuristic-based algorithms that is guaranteed to find the least-cost path to a goal state if the heuristic used is admissible, which means that it never overestimates the real cost from the current state to the goal. In this article, we are going to present a neural network architecture that makes it possible to predict admissible heuristics for a given graph and destination node, then we are going to refine our models using genetic algorithms in order to obtain better results.