Matthew Stephenson

Procedural generation of complex stable structures for angry birds levels

This paper presents a procedural content generation algorithm for the physics-based puzzle game Angry Birds. The proposed algorithm creates complex stable structures using a variety of 2D objects. These are generated without the aid of pre-defined substructures or composite elements. The structures created are evaluated based on a fitness function which considers several important structural aspects. The results of this analysis in turn affects the likelihood of particular objects being chosen in future generations. Experiments were conducted on the generated structures in order to evaluate the algorithms expressivity. The results show that the proposed method can generate a wide variety of 2D structures with different attributes and sizes.

Generating varied, stable and solvable levels for angry birds style physics games

This paper presents a procedural level generation algorithm for physics-based puzzle games similar to Angry Birds. The proposed algorithm is capable of creating varied, stable and solvable levels consisting of multiple self-contained structures placed throughout a 2D area. The work presented in this paper builds and improves upon a previous level generation algorithm, enhancing it in several ways. The structures created are evaluated based on a updated fitness function which considers several key structural aspects, including both robustness and variety. The results of this analysis in turn affects the generation of future structures. Additional improvements such as determining bird types, increased structure diversity, terrain variation, difficulty estimation using agent performance, stability and solvability verification, and intelligent material selection, advance the previous level generator significantly. Experiments were conducted on the levels generated by our updated algorithm in order to evaluate both its optimisation potential and expressivity. The results show that the proposed method can generate a wide range of 2D levels that are both stable and solvable.

Deceptive angry birds: towards smarter game-playing agents

Over the past few years the Angry Birds AI competition has been held in an attempt to develop intelligent agents that can successfully and efficiently solve levels for the video game Angry Birds. Many different agents and strategies have been proposed to solve the complex and challenging physical reasoning problems associated with such a game. The performance of these agents has increased significantly over the competitions lifetime thanks to the different approaches and improved techniques employed. However, there still exist key flaws within the designs of these agents that can often lead them to make illogical or very poor choices. Most of the current approaches try to identify the best or a good next shot, but do not attempt to plan an effective sequence of shots. While this might be due to the difficulty in predicting the exact outcome of a shot, this capability is precisely what is needed to succeed, both in games like Angry Birds, but also in the real world where physical reasoning capabilities are essential. In order to encourage development of such techniques, we can create levels where selecting a seemingly good next shot will lead to a worse outcome. In this paper we present several categories of deception to fool the current state-of-the-art agents. By evaluating the performance of the most recent Angry Birds agents on specific level examples that contain these deceptive elements, we can show how certain AI techniques can be tricked or exploited. We also propose some ways that future agents could help deal with these deceptive levels to increase their overall performance and generality.

Introducing real world physics and macro-actions to general video game ai

The General Video Game AI Framework has featured multiple games and several tracks since the first competition in 2014. Although the games of the framework are very assorted in nature, there is an underlying commonality with respect to the physics that govern the game: all of them are based on a grid where the sprites make discrete movements, which is not expressive enough to cover any meaningful physics. This paper introduces an enhanced physics system that brings real-world physics such as friction, inertia and other forces to the framework. We also introduce macro-actions for the first time in GVGAI in two different controllers, Rolling Horizon Evolution and Monte Carlo Tree Search. Their usefulness is demonstrated in a new set of games that exploits these new physics features. Our results show that macro-actions can help controllers in certain situations and games, although there is a strong dependency on the game played when selecting which configuration fits best.