Optimists at Heart: Why Do We Research Game AI?

Cook, Michael

doi:10.1109/cog51982.2022.9893607

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work's pilot experiments make use of the Mario AI Benchmark, a widely used AI research platform used for the development and evaluation of AI agents for level playing and level generation. While we share the sentiment of Mike Cook that Super Mario has received an unreasonable amount of focus within PCG literature as a test bed [4] , using it within this work is justified by the amount of prior work that has applied ERA specifically to Mario level generators. This gives us both a wide variety of previously used metrics to draw upon, as well as making any insights we gain into optimal metric selection more relevant to the research community.…”

Section: Mario Ai Benchmarkmentioning

confidence: 99%

“…An important concept for this work, but also ERA more broadly, is that of generative spaces and possibility spaces. These terms were popularised by Mike Cook in their work [4] and they help to highlight the strengths and weaknesses of ERA, as well as the potential benefits of this work's approach. Unfortunately the definition of these terms is not universally accepted, and there are high profile works that use generative space and possibility space interchangeably [10].…”

Section: Generative Space Possibility Spaces and Eramentioning

confidence: 99%

See 1 more Smart Citation

The Right Variety: Improving Expressive Range Analysis with Metric Selection Methods

Withington

Tokarchuk

2023

Proceedings of the 18th International Conference on the Foundations of Digital Games

View full text Add to dashboard Cite

Expressive Range Analysis (ERA), an approach for visualising the output of Procedural Content Generation (PCG) systems, is widely used within PCG research to evaluate and compare generators, often to make comparative statements about their relative performance in terms of output diversity and search space exploration. Producing a standard ERA visualisation requires the selection of two metrics which can be calculated for all generated artefacts to be visualised. However, to our knowledge there are no methodologies or heuristics for justifying the selection of a specific metric pair over alternatives. Prior work has typically either made a selection based on established but unjustified norms, designer intuition, or has produced multiple visualisations across all possible pairs. This work aims to contribute to this area by identifying valuable characteristics of metric pairings, and by demonstrating that pairings that have these characteristics have an increased probability of producing an informative ERA projection of the underlying generator. We introduce and investigate three quantifiable selection criteria for assessing metric pairs, and demonstrate how these criteria can be operationalized to rank those available. Though this is an early exploration of the concept of quantifying the utility of ERA metric pairs, we argue that the approach explored in this paper can make ERA more useful and usable for both researchers and game designers. INTRODUCTIONProcedural Content Generation (PCG) systems for games can often produce huge amounts of diverse artefacts and experiences. Whether it is the billions of possible maps of Minecraft [18] or the quintillions of planets in No Man Sky [6], the total volume of a PCG system's possible output, commonly referred to as its 'generative space' can be huge and complex. The challenge of understanding and usefully comparing generative spaces is a vital one to both

show abstract

Section: Mario Ai Benchmarkmentioning

confidence: 99%

Section: Generative Space Possibility Spaces and Eramentioning

confidence: 99%