Demonstrating Automatic Content Generation in the Galactic Arms Race Video Game

Abstract

In most modern video games, content (e.g. models, levels, weapons, etc.) shipped with the game is static and unchanging, or at best, randomized within a narrow set of parameters. However, if game content could be constantly renewed, players would remain engaged longer. To realize this ambition, the content-generating NeuroEvolution of Augmenting Topologies (cgNEAT) algorithm automatically evolves novel game content based on player preferences, as the game is played. To demonstrate this approach, the Galactic Arms Race (GAR) video game, which incorporates cgNEAT, will be presented. In GAR, players pilot space ships and fight enemies to acquire novel particle system weapons that are evolved by the game. The live demo will show how GAR players can discover a wide variety of weapons that are not only novel, but also based on and extended from previous content that they preferred in the past. The implication of cgNEAT is that it is now possible to create games that generate their own content, potentially significantly reducing the cost of content creation and increasing the replay value of games.

Towards a Generic Method of Evaluating Game Levels

“…Recent academic interest in procedural game content generation has also been directed towards the creation of game levels for existing games such as Starcraft (Togelius et al 2010) or TORCS (Cardamone, Loiacono, and Lanzi 2011). Many of these applications use search-based processes (Togelius et al 2011) such as genetic algorithms, which require an evaluation function in order to select the most appropriate content for reproduction; these evaluations can be provided directly or indirectly by humans (Hastings, Guha, and Stanley 2009;, or can be formulated mathematically according to predicted entertainment (Pedersen, Togelius, and Yannakakis 2010) or concepts popularized by successful games such as chokepoints (Togelius et al 2010). Sorenson and Pasquier (2010) propose a generic framework for level generation using a Feasible-Infeasible two-population Genetic Algorithm, and show its potential in platformer game levels and 2D adventure games.…”

The Future of Procedural Content Generation in Games

“…The few multiplayer games that use PCG, such as Civilization IV, are typically creating content that is in a single instance-maps that many players will interact but are the same for each player. There are very few games that have multiplayer, multi-instance PCG, where multiple players are interacting with unique, realtime generated content that is based on the behavior of multiple players-Galactic Arms Race comes close, with weapons tailored for individuals that are born from a pool that is available to all players (Hastings, Guha, and Stanley 2009)-or that can influence what other players will see in their own version of the game.…”

“…Even the most innovative games typically use PCG in similar ways and for similar aesthetic goals. The aesthetics of discovery and challenge are common to most games that use PCG, and even games that use PCG as a mechanic (Hastings, Guha, and Stanley 2009;Risi et al 2012;G. Smith et al 2012).…”

Designing Procedurally Generated Levels

“…Procedural content generation (PCG) concerns itself with the algorithmic creation of content. The potential benefits of using PCG in games are already well established: (i) the rapid reliable generation of game content (Smith and Mateas 2011), (ii) the increased variability of the generated content (Hastings, Guha, and Stanley 2009;, and (iii) its use to support player-centered adaptive games (Lopes and Bidarra 2011;Yannakakis and Togelius 2011). However, these benefits highly depend on an essential feature of any generative method: the degree of control over the generator.…”