Planning is branch in artificial intelligence that tries to create general solvers that can solve any problem described by the set: .
Planners try to solve the different problems by deploying a graph in which nodes represent the problem states and conducting forward search to find the optimal path from the initial state to the goal state. The number of states in a problem is exponential in the number of predicates in the problem and therefore it is sometimes impossible to deploy the whole graph or/and to find the optimal path. To overcome this problem, the search methods use heuristic functions which allows the search advancing only in specific directions and makes the search possible. In this project we found a method to approximate the optimal plan length using machine learning models, and particularly using Graph Neural Networks.