Procedural Content Generation for General Video Game Level Generation

With the passage of time, video games are becoming more complex, and their development incurs greatertime and cost. The creation of video gaming content such as levels, maps, textures and so on represent a largepart of the overall cost of game development. Procedural Content Generation (PCG) is a method of generatingcontent via a pseudo-random process. Level generation has been the most significant and oldest problem in thePCG domain. The majority of the PCG level generators are specific to a particular game, content is generatedonly for a suited single type and these generators are evaluated mostly by computational metrics, user studiesand fitness functions. Considering, the grand goal of general Artificial Intelligence, it would be beneficial to sculptsolutions that are applicable to a general set of problems. For the level generation problem, this can be achievedby constructing a level generator that generates levels for a set of games and not explicitly for a single game. Inthis research, we have created four different type of generators for the GVG-LG framework. The generators followa distinct path and are able to solve multiple problems related to PCG including dynamic difficulty adjustment,creation of intelligent controllers, creating aesthetically appealing levels and using patterns as objectives for levelgeneration. In addition, we evaluated all the generators using a variety of techniques. The experimental resultsshow promising results and represent our attempt at general video game level generation.