A search-based approach for generating Angry Birds levels

Abstract

This paper presents a genetic algorithm (GA) for the procedural generation of levels in the Angry Birds game. The GA evaluates the levels based on a simulation which measures the elements' movement during a period of time. The algorithm's objective is to minimize this metric to generate stable structures. The level evaluation also considers some restrictions, leading the levels to have certain characteristics. Since there is no open source code of the game, a game clone has been developed independently of our algorithm. This implementation can be used to support experiments with procedural content generation (peG) methods for this game type. We performed experiments in order to evaluate the expressivity of the level generator and the results showed that the proposed algorithm could generate levels with interesting stable structures.

Procedural Puzzle Generation: A Survey

“…Ferreira and Toleda used a genetic algorithm to generate levels for another popular 2D physics puzzle game: Angry Birds (2009) [46]. Briefly, the objective in Angry Birds is to crush all the pigs, in the alloted time, by using a slingshot to throw birds against a structure of blocks and pigs.…”

“…The results of each simulation-specifically the average velocity and number of collisions for the blocks and pigs, plus end rotation for the blocks-are recorded for use in determining the stability of structures in a level. The genetic algorithm considers the most fit levels to be those that are the most stable and performs crossover and mutation by manipulating the associated arrays of columns [46].…”

Artificial Intelligence Based Game Levelling

“…In [11], dynamic difficulty adjustment is provided by Polymorph approach which changes game difficulty depending on player performance. In the literature, there are various studies that are designed by machine learning (genetic algorithm, artificial neural network, support vector machine) [12][13][14][15][16], probabilistically techniques [17], Procedural Content Generation (PCG) [18][19][20] for dynamic game levelling. The difficulties caused by the behavior of NPC objects can be supported by artificial intelligence applications to maximize a user's enjoyment.…”

A Spatially-Structured PCG Method for Content Diversity in a Physics-Based Simulation Game

“…For example, Julian Togelius et al, designed a SBPCG multiobjective evolutionary algorithm whose objective was create maps for realtime strategy [14,15] and racing [16] games. In a similar way, Ferreira and Toledo [17] presented a SBPCG approach for generating levels for the physicsbased videogame Angry Birds. Lara et al [18] presented a search-based procedural content generation method in the context of the real-time strategy game 3 Planet Wars (i.e., the Google AI Challenge 2010) whose objective was to generate maps that resulted in an interesting gameplay, focusing on properties of balance and dynamism.…”