Shedding some light on Light Up with Artificial Intelligence

TL;DR

This paper explores modern AI techniques like neural networks and simulated annealing to solve the Light-Up puzzle more efficiently, outperforming traditional evolutionary algorithms in accuracy and speed.

Contribution

It introduces the application of neural networks and simulated annealing to the Light-Up puzzle, demonstrating improved accuracy and computational efficiency over existing methods.

Findings

Simulated annealing achieved 100% accuracy on test configurations.

Neural networks were faster but less accurate.

Algorithms with 3 actions outperformed those with 2 actions.

Abstract

The Light-Up puzzle, also known as the AKARI puzzle, has never been solved using modern artificial intelligence (AI) methods. Currently, the most widely used computational technique to autonomously develop solutions involve evolution theory algorithms. This project is an effort to apply new AI techniques for solving the Light-up puzzle faster and more computationally efficient. The algorithms explored for producing optimal solutions include hill climbing, simulated annealing, feed-forward neural network (FNN), and convolutional neural network (CNN). Two algorithms were developed for hill climbing and simulated annealing using 2 actions (add and remove light bulb) versus 3 actions(add, remove, or move light-bulb to a different cell). Both hill climbing and simulated annealing algorithms showed a higher accuracy for the case of 3 actions. The simulated annealing showed to significantly outperform hill climbing, FNN, CNN, and an evolutionary theory algorithm achieving 100% accuracy in 30 unique board configurations. Lastly, while FNN and CNN algorithms showed low accuracies, computational times were significantly faster compared to the remaining algorithms. The GitHub repository for this project can be found at https://github.com/rperera12/AKARI-LightUp-GameSolver-with-DeepNeuralNetworks-and-HillClimb-or-SimulatedAnnealing.