Tanager: A Generator of Feasible and Engaging Levels for Angry Birds

Generating feasible levels for physics-based puzzle games is a complex and time-consuming task. This is because the mechanics of these games are based on realistic physics, so simulations are required to evaluate the playability of the generated levels. Recently, a few generators have been able to produce considerably complex levels in the context of the Angry Birds game, a very famous title of this genre. However, none of these generators are able to guarantee the playability of their produced levels. This paper presents Tanager, a level generator based on a genetic algorithm that is capable of producing feasible levels for the Angry Birds game. Evaluating playability in this game requires checking both the stability of the stacked blocks and the possibility of killing all the pigs with the given amount of birds. These two components are handled by the algorithm through a simulation. The first one is calculated by measuring the overall velocity of the blocks and the second is defined by an intelligent agent, which plays the levels. Three sets of experiments are conducted to evaluate Tanager. The first one measures the performance of the genetic algorithm underneath Tanager. The second one explores the expressivity of the generated levels considering their structural characteristics. The third one measures design quality of levels via an online user study. Results show that Tanager is capable of generating a considerable variety of feasible levels that are as engaging and enjoyable as those manually designed. However, the generated levels are less challenging than the hand-authored ones.

[1]  Claudio Fabiano Motta Toledo,et al.  Generating levels for physics-based puzzle games with estimation of distribution algorithms , 2014, Advances in Computer Entertainment.

[2]  Kalyanmoy Deb,et al.  Multi-objective Optimisation Using Evolutionary Algorithms: An Introduction , 2011, Multi-objective Evolutionary Optimisation for Product Design and Manufacturing.

[3]  Clark Verbrugge,et al.  Generative Methods for Guard and Camera Placement in Stealth Games , 2014, AIIDE.

[4]  Jochen Renz,et al.  Procedural Generation of Levels for Angry Birds Style Physics Games , 2021, AIIDE.

[5]  Julian Togelius,et al.  Evolving Playable Content for Cut the Rope through a Simulation-Based Approach , 2013, AIIDE.

[6]  Daniele Loiacono,et al.  TrackGen: An interactive track generator for TORCS and Speed-Dreams , 2015, Appl. Soft Comput..

[7]  Levi Lelis,et al.  A Computational Model Based on Symmetry for Generating Visually Pleasing Maps of Platform Games , 2016, AIIDE.

[8]  Gillian Smith,et al.  Analyzing the expressive range of a level generator , 2010, PCGames@FDG.

[9]  Julian Togelius,et al.  The 2009 Mario AI Competition , 2010, IEEE Congress on Evolutionary Computation.

[10]  Julian Togelius,et al.  Sentient Sketchbook: Computer-aided game level authoring , 2013, FDG.

[11]  Ruck Thawonmas,et al.  Procedural generation of angry birds levels with adjustable difficulty , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[12]  Paul A. Cairns,et al.  Measuring and defining the experience of immersion in games , 2008, Int. J. Hum. Comput. Stud..

[13]  Julian Togelius,et al.  Automatic generation and analysis of physics-based puzzle games , 2013, 2013 IEEE Conference on Computational Inteligence in Games (CIG).

[14]  Claudio Fabiano Motta Toledo,et al.  Learning to Speed Up Evolutionary Content Generation in Physics-Based Puzzle Games , 2016, 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI).

[15]  Daniele Loiacono,et al.  Evolving maps for match balancing in first person shooters , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[16]  Julian Togelius,et al.  Search-Based Procedural Content Generation: A Taxonomy and Survey , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[17]  Rafael Bidarra,et al.  Procedural Generation of Dungeons , 2014, IEEE Transactions on Computational Intelligence and AI in Games.

[18]  Claudio Fabiano Motta Toledo,et al.  A search-based approach for generating Angry Birds levels , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[19]  Peng Zhang,et al.  Qualitative Spatial Representation and Reasoning in Angry Birds: The Extended Rectangle Algebra , 2014, KR.

[20]  W. G. Smith,et al.  Angry Birds , 1888, Nature.

[21]  Mike Stilman,et al.  Robot Jenga: Autonomous and strategic block extraction , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  R. Lyndon While,et al.  Applying evolutionary algorithms to problems with noisy, time-consuming fitness functions , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[23]  Julian Togelius,et al.  Procedural Content Generation in Games , 2016, Computational Synthesis and Creative Systems.